Survey
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
PSU Research Proposal Title: Satellite Data Mining: Mining Environmental Satellite Data- An Application on Locating Potential Water Resources Department: Computer Science PI Name: Ahmed Sameh Duration: 2 years Budget Est: SR 79,000 Date: 12/20/2010 0 I - PROPOSAL I-1: PROPOSAL TITLE (Provide a short descriptive title, give prominence to keywords) Satellite Data Mining: Mining Environmental Satellite Data- An Application on Locating Potential Water Resources I-2: COMMERCIAL POTENTIAL Yes Could this project have commercial potential? (Select one) No If yes, briefly elaborate on the commercial potential The Saudi Geological Survey in Jeddah as well as the Saudi Military Geological Survey in Riyadh might be interested in acquiring the developed system. The methodology proposed in this project is new; we could apply for a patent after proving its success. I-3: CHECK-LIST Have you checked to ensure all questions in the application form have been answered? Have you checked to ensure you have included the correct costs in your budget? The principal investigator and all co-principal investigators should sign. I-4: PERSONNEL AND AUTHORIZATION PRINCIPAL INVESTIGATOR [PI] Academic Rank: Professor College: Telephone: Full Name: Ahmed Sameh Department: Computer Science CIS 494-8524 Ext: X8524 Mobile: 05044299846 E-Mail: [email protected] Signature: CO- INVESTIGATOR(S) [CIs] 1) Date: (non-PSU CIs permitted) Full Name: Mohamed Sultan (Western Michigan University) Academic Rank: Professor College: Telephone: E-Mail: Department: Mobile: 1 12/20/2010 Signature: 2) Date: Full Name: / Date: / / Date: / / Date: / / Full Name: Fakhry Khellah College: E-Mail: Department: Computer Science CIS Telephone: Mobile: Signature: Date: Full Name: Khalid Al-Mustafa Academic Rank: Assistant Professor College: CIS Telephone: E-Mail: Department: Information System Mobile: Signature: Full Name: Academic Rank: College: Telephone: Ayman Kassem (King Fahd University) E-Mail: Department: Mobile: Signature: 6) / Date: Academic Rank: Assistant Professor 5) / Mobile: Signature: 4) / E-Mail: Department: Computer Science CIS Telephone: 3) / Rashid Zantout Academic Rank: Associate Professor College: / Full Name: Academic Rank: College: Telephone: E-Mail: Department: Mobile: Signature: 2 II - DESCRIPTION II-1: ABSTRACT (Provide a statement of the project - maximum 200 words) This project explores the area of “Multi-Media Data Mining”. In particular “Satellite Images” are usually the target of traditional “Remote Sensing” research. Satellite data mining will expand on traditional image remote sensing operations to reveal hidden knowledge embedded in such rich collection of satellite images utilizing text background knowledge databases. The research will target Saudi Arabia’s needs from mining its satellite images. It will serve some important necessities such as: military boarder surveillance, monitoring ‘hot spots’, identifying exposed artifacts by international rooming spay satellites, Oil and mineral resource exploration, monitoring oil spills, classification of vegetation regions, discovering both above and underground waterpockets, monitor Atmospheric conditions (e.g. water vapor, wind patterns, air temperature), predict climate changes, and explore phenomena such as “Tashahor”, “Flooding”, and Cities Urban planning. The project will deliver an integrated system developed on top of standard platform of fast Oracle databases of Saudi satellite images composed of its different regions at different resolutions supported by clever images’ indexing techniques. It will also build a powerful library of algorithms on top of standard Matlab image processing toolbox using GIS data. The integrated system will be unique in targeting the above Saudi’s needs in such comprehensive and cross-correlated manner mixing both images databases and text background knowledge databases. Previous research in remote sensing applies specific algorithms on images for specific purpose. The proposed system correlates different needs and discover inter-relations that never been investigated before through data mining at different fronts (both inter- and intra-). For example, correlating “Tashahor” with wind patterns and soil moisture prediction will make use of three types of images databases (Tashahor, winds, and soil) along with a text background knowledge database that stores previous knowledge about these issues specific for Saudi Arabia. Such unique feature of the proposed system is close to integrating “Remote Sensing”, “Geographical Information System” with “Data Mining”. To our knowledge such federation of databases and techniques never been investigated before. The project will focus its scope to one area at a time. As a starter we will explore the rich area of Saudi geological data, background knowledge, and specific hydrologic investigation queries. Domain-specific experts and historical knowledge will be the main source of background text data. The Saudi Geological Survey (SGS) agency will be the main source of images and text data. One of the investigators is working in a research project investigating Land Slides near Jeddah. He also has been working on the Empty quarter in a previous research project. Other image data will be collected and/or purchased from commercial Internet satellite agencies. At this point in time, the SGS is providing us with data about Al Robh El-Kaly (Empty Quarter). Data about annual precipitation, field region gauges, and aquifer characteristics of rocks at this area are provided. In summary, this project will deliver both a new methodology (with an implemented prototype), as well as new results in the area of application of the methodology. 3 II-2: PROJECT GOALS AND OBJECTIVES The main objectives of this project is to build a Saudi Multi-media data mining architecture that is open, light weight, and distributed relying on standard databases and data mining techniques. The end product should be able to answer both Intra-Correlation queries and Inter-Correlation queries. In answering these queries, we target the following goals and objectives: 1- Better understanding of the interplay of mixing remote sensing operations with background knowledge 2- Effective decoupling of the data mining algorithms, background knowledge, and the image databases 3- Efficient acceleration of the federation of databases for fast data accesses 4- Flexible scripting of the queries within the architecture to implement an open system 5- Distributed architecture (Client/Server) with web support 6- Use of standard databases and remote sensing operations 7- Building solid and reliable supporting infrastructure centered around users’ needs 8- Maintaining security and privacy issues 9- Monitoring System requirement changes 10- Ensuring scalability and abstraction of functionality 11- Assure effective responses to both Intra- and Inter- Correlation queries 12- Ensure efficient deployment (minimal client installation and on-demand dynamic loading of components) 12- Provide appropriate visual results interpretation 13- Provide several scenario based validations (openness, completeness, and efficiency) 14- Ability of future porting of the client side to other platforms (e.g. Mobile) 15- Support for future advanced data mining algorithms that can for example combine semantic interpretations and retrieve/correlate satellite image patches 16- Deliver military queries such as observe deployment of military forces, weapons development, assessment of damage caused by bombs and also provide intelligence on enemy capabilities, nuclear compliance and missile launches 17- Support more complex queries that involve automatic semantic categorization of images (higher-order semantic that focus on both spectral and spatial dimensions) Through out this research we will be targeting two categories of characteristics through which we can define various measures of success. The two categories of characteristics are: measurable functionality characteristics and measurable performance characteristics. The implemented architecture should provide the following characteristics (measurable functionalities): 1- Easy entry of collected data; both images and background knowledge 2- Transparency of correlation details from the web client point of view 2- Flexible formulation of both Intra- and Inter- Correlation queries 3- Effective and efficient graphical user interface 4- Practical visualization display of results 5- Capability of low level investigation of low and intermediate operations 6- Exposing faced difficulties en route of answering queries As for the performance non-functional expectations: 1- Easy single point of service deployment 2- Openness and scalability through supporting addition of new data mining methods and/or databases to the system 3- Better utilization of bandwidth and speeds of data transfer over the network 4- Security and privacy issues 5- Light weight system implementation 6- Flexibility to handle diverse applications (e.g. military, exploration) 4 III - INTRODUCTION III-1: REVIEW AND ANALYSIS OF RELATED WORK Multi-media data mining is more general than traditional data and text mining. It deals with a combination of text, audio, still images, animation, video and interactivity contents. In this project we limit our scope to only text, and still satellite images. Data mining of such contents is building on top of remote sensing capabilities that same way that computer vision research builds on top of low level image processing capabilities. Remote sensing is defined as the science and technology by which the characteristics of objects of interest can be identified, measured or analyzed without direct contact. Remote sensing replaces costly and slow data collection on the ground, ensuring in the process that areas or objects are not disturbed. The most established markets in remote sensing are in the areas of natural resources such as exploration of oil, gas, nd minerals; military spying, classification of vegetation regions, discovering underground waterpockets, monitor Atmospheric conditions (e.g. water vapor, wind patterns, air temperature), and predict climate changes. There are three main problems with remote sensing which are: (1) the enormously growing volume of imagery (e.g. Multi/hyper spectral of different formats) with lots of time consuming preprocessing; (2) they allow only for simple queries of sensory data; and (3) they lack efficient retrieval of useful information since there is lots of complex spatial/tem-oral associations. The proposed project will resolve these traditional problems and will expand on image remote sensing operations to reveal hidden knowledge embedded in such rich collection of satellite images of Saudi Arabia utilizing text background knowledge databases. Text background knowledge databases are databases that store relevant background knowledge specific to Saudi Arabia with regards to the specific investigation area. For example, previously known knowledge about “Flooding” regions in the Kingdom and the previous experience gain from such historical events are collected and coded into such text background databases. As another example, oil spills occur both in the open sees and along the coasts, so background information about major shipping routes and anchorage areas will help in locating potentially vulnerable areas. Similar information about gas, and minerals; military boarder previous events, information about ‘hot spots’ such as holy places, knowledge about classification of vegetation regions in the Kingdom, information about both above and underground known waterpockets, background information about previous Atmospheric conditions (e.g. water vapor, wind patterns, air temperature) in certain regions at certain times, and background knowledge about “Tashahor” areas are all collected and coded in the text background databases. The proposed system will be unique in targeting the above Saudi’s queries in such comprehensive and crosscorrelated manner mixing both images databases and text background knowledge databases. Previous research in remote sensing applies specific image processing algorithms such as image registration, and object recognition on images for specific purpose. The proposed system will correlate different queries and discover inter-relations between image and text data that never been investigated before through data mining at different fronts (both intra- and inter-). Intra-Correlations means cross-correlating images databases and text background databases for a specific type of queries. For example in exploring new underground waterpockets in “Aseer” area, the proposed system will mine collection of “Aseer” satellite images for waterpocket detections (certain resolutions with specific filters), and text background knowledge databases related to this issue. Inter-Correlation means cross-correlating heterogeneous images databases and text background databases to answer mixed-type queries. For example, answering queries about the relationship of “Tashahor” with wind patterns and soil moisture in “Aseer” will make use of three types of images databases (Tashahor, winds, and soil) along with a text background knowledge database that stores previous knowledge about these issues specific for “Aseer”. Such unique feature of the proposed system is close to integrating “Remote Sensing”, “Geographical Information System” with “Data Mining”. For example, how pre-classification image segmentation will interplay with lower resolution background knowledge? To our knowledge such federation of databases and techniques never been investigated before. Existing research prototypes that are similar to the proposed systems are: (1) The ITSC Algorithm development and Mining (Adam) System [5]; (2) NASA JPL Diamond Eye System [6]; (3) DLR Intelligent Satellite Information Mining System [7]; and (4) The Insightful VisiMine System [8] ADaM was developed at the University of Alabama in response to the need to mine large scientific data sets for geophysical phenomena detection and feature extraction. It provides knowledge discovery and data mining capabilities for data values, as well as for metadata, and catalogs the information discovered. It contains algorithms for detecting a variety of geophysical phenomena to address the needs of the Earth Science community. 5 Diamond Eye , developed at Jet Propulsion Lab, California Institute of Technology, is an image mining system that enables scientists to locate and catalog objects of interest in large image collections. This system provides a platform-independent interface to novel image mining algorithms, as well as to computational and a database resources that allow scientists to browse, annotate and search through images and analyze the resulting object catalogs. The German Aerospace Center DLR has created an intelligent satellite information mining system as a next generation architecture to help users to gather rapidly information during courses of actions. This is a tool to add value and to manage the huge amount of historical and newly acquired satellite data-sets by giving to experts access to relevant information in an understandable and directly usable form and to provide friendly interfaces for information query and browsing. VisiMine is an interactive mining system for image databases. It is developed by the Insightful corporation in Seattle. VisiMine is a system for data mining and statistical analysis of large collection of remotely sensed images. It provides an environment for high-interaction graphical analysis of multivariate data, modern statistical methods, data clustering and classification, and mathematical computing. None of the above research prototypes supports the proposed integrated Intra- Inter- correlation queries or makes use of the background knowledge. The proposed project use the methodology of “Data Fusing” to bring together multiple sources of data and apply data mining algorithms in order to reveal hidden and inferred knowledge. III-2: SIGNIFICANCE OF WORK Findings: This project takes the field of remote sensing to higher grounds by applying knowledge discovery techniques of data mining utilizing a set of background knowledge. Intra- and Inter- Correlation queries and the federation of both images and text databases are new concepts in the field of remote sensing. It is our hope that applying such new concepts will lead to interesting finding at the various areas of Saudi’s needs. The project will deliver a prototype implementation of the proposed architecture. The prototype will have all the functional and non-functional specifications listed in this proposal. A number of Intra- and InterCorrelation queries will be supplies within the prototype in the areas of military boarder sullivaliance, monitoring ‘hot spots’, identifying exposed artifacts by international rooming spay satellites, Oil and mineral resource exploration, monitoring oil spills, classification of vegetation regions, discovering both above and underground waterpockets, monitor Atmospheric conditions (e.g. water vapor, wind patterns, air temperature), predict climate changes, and explore phenomena such as “Tashahor”, “Flooding”, and Cities Urban planning. The Saudi Geological Survey in Jeddah as well as the Saudi Military Geological Survey in Riyadh might be interested in acquiring the developed system. The methodology proposed in this project in new, we could apply for a patent after proving its success. Publications: A number of research publications are expected out of this research: A journal paper plus at least two conference papers. Also a number of research presentations will be produced. This research introduces data mining and knowledge-based guidance in remote sensing of images. It presents an integrated remote sensing image information mining framework and proposed a prototype implementation. It shows how to evolve the prototype into a practical tool and how to apply it into specific applications (e.g. agricultural and environmental monitoring) when enough data is available. IV - APPROACH AND METHODOLOGY IV-1: METHODOLOGY 6 The project will deliver an integrated system (See figure) developed on top of standard platform of fast Oracle databases of Saudi satellite images composed of its different regions at different resolutions supported by clever images’ indexing techniques. Oracle is a powerful database management system that can deal efficiently and effectively with both text and image data. We will use image enhancement add-on of Oracle (plug-in of Oracle) to accelerate both storage and retrieval of the large collection of images. The client’s GUI provide functionality for Queries, Browsing, and visualization. Indexing techniques are implemented for both images and text knowledge databases. The data mining algorithms such as: Principal Component Analysis (PCA), texture feature extraction, clustering, and spectral analysis algorithms for land cover classification are implemented as Matlab scripts on top of its image processing toolbox. Oracle add-on imagining provides various indexing techniques such as spatial indexes (e.g. Quadtree, Octree, Grid, X-tree, and R-tree) for efficient image retrieval. In the future content-based retrieval may be investigated to semantically chunk patches of images and cluster them by category, proximity, temporally. The server will build a powerful library of algorithms on top of standard Matlab image processing toolbox. The library will be basically a set of Matlab scripts that implements main remote sensing functions. For example, time series analysis of time stamped sequence of images, images registration and spatial transformation, images classification, object recognition, morphological transforms, and images analysis and statistics. For example detecting changes in images over time. These differences may be due to actual change in land cover, or differences in illumination, atmospheric conditions, sensor calibration or ground moisture conditions. This relates to image registration with post-classification comparison, multi-date classification, image regression, image rationing, principal components analysis, and change vector analysis. Background knowledge databases are resembling GIS systems’ information but with artificial intelligence flavor of reasoning and deduction capabilities. These text data will be stored in object-oriented databases and will store specific information about Saudi Arabia. For example background information about Saudi’s boarders strong points, locations of ground surveillance troops, and types of military equipments distributed at these locations. Also background information about previous historical floods in Saudi Arabia with statistical information and experiences gained at these time. History of previous climate changes happened through the Kingdom with background information about the reasons and the effects of such changes. The server will utilize some data mining algorithms such as image classification, clustering, association and forecasting algorithms. For example Self-Organizing Map (SOM) clustering can be used for pre-processing of images to produce more informed segmentation for complex images. K-means clustering can be used to partition the texture feature space into subspaces in terms of the various image classes. Data mining classification can be used to produce better indexing techniques for the huge number of images. Association rules and decision trees can be used to correlate shape features, and spatial-temporal relationships. The proposed system is based on standards components: Oracle, Matlab, and Data Mining tools. Saudi satellite images and text data will be collected from the Saudi Geological Survey agency in Jeddah [4]. Other background data and images will be collected and/or purchased from commercial sites on the Internet. As such the project’s feasibility has been proven. Graphical User Interface Image Repository PCA Land Cover Classification Texture Feature Extraction Browsing / Query Databases Module ObjectOriented Database Clustering Image Database Image Processing Module Figure 1: One possible function of the proposed System that combines DM + RS + GIS + Background Knowledge The project will focus its scope to one area at a time. As a starter we will explore the rich area of Saudi geological data, background knowledge, and specific hydrologic investigation queries. Domain-specific experts and historical knowledge will be the main source of background text data. The Saudi Geological 7 Survey (SGS) agency will be the main source of image and text data. Other image data will be collected and/or purchased from commercial Internet satellite agencies. At this point in time, the SGS is providing us with data about Al Robh El-Kaly (Empty Quarter). Data about annual precipitation, field region gauges, and aquifer characteristics of rocks at this area are provided. In summary, this project will deliver both a new methodology as well as new results in the area of application. Figure 2: High Level System Architecture of the proposed system We will then move to define a wide scope of the proposed system, then designing and building the main architecture, collect relevant images and knowledge data in order to populate the databases, then start testing the system’s functionality through a number of Intra- and Inter- Correlation queries. We then investigate the performance characteristics. Finally narrowing the project focus to a specific area of investigation (e.g. military, climate, oil, vegetation) will depend on the rich data that we will find to allow such deeper investigations. Scope: The project will deliver a prototype implementation of the proposed architecture. The prototype will have all the functional and non-functional specifications listed in this proposal. A number of Intra- and InterCorrelation queries will be supplied within the prototype in the areas of military boarder surveillance, monitoring ‘hot spots’, Oil and mineral resource exploration, monitoring oil spills, classification of vegetation regions, discovering underground water pockets, monitor Atmospheric conditions (e.g. water vapor, wind patterns, air temperature), and predict climate change. As time passes, the project scope will focus further. As a starter we will explore the above wide areas (military, oil, vegetation, climate) until we stumble into a rich area with data, background knowledge, and specific investigation queries. Work breakdown structure- Deliverables:- who does what- see the Gantt Chart below System requirements specifications: Sameh System Architecture : Sultan System Design: Sameh, Rashid Databases Designs: Khalid 8 Matlab Scripts Design: Fakhry Prototyping of critical sub-systems: Rashid, Sameh System Detailed Design: Sameh, Sultan Beta Version Implementation: Sameh, Khalid Testing: Fakhry Building Deployment Environment: Rashid Bench Marking and Collecting Results (First Round): Sameh System Tuning (Based on First Round Results): Khalid, Ali Bench Marking and Collecting Results (Second Round Results): Fakhry System Tuning (Based on Second Round Results): Sameh, Faisal Bench Marking and Collecting Results (Third Round Results): Rachid Version 1 Release Results Documentation and Analysis with the Performance requirements Detailed Code Documentation: Faisal User and Installation Guide (Full How To): Ali Methods: Saudi Satellite images will be collected from the Saudi Geological Survey Agency in Jeddah [4], and from the Internet. There are many sites that sell satellite images (see [1][2][3]). There are various types of satellite images. For example, visible imagery are day time pictures that show clouds as white, the ground as grey, and water is darker. Terrain features such as rivers are lakes can be identified. Thunderstorm cloud building can be detected. Infrared imagery measures heat radiation off surfaces. Whereas Water vapor imagery measures moisture in the atmosphere. They also come at different resolutions (pixel size represents surface area measured on the ground), different spectral resolutions (wavelength interval size on the Electromagnetic spectrum), and different radiometric resolutions (several levels of brightness). It is important to choose the image types that are suitable for the task under consideration. Background Saudi information to populate the knowledge bases will be collected from various sources such as ministries, the Saudi geological Survey Agency, and government information systems. As for the exposed areas of Saudi Arabia that are exposed to spy satellites, we will collect information about currently rooming satellites on top of the Kingdom. We will store information about the payload of each satellite and its spying capabilities. The system will mine these information to answer queries about “what others are looking at?” Data collection expected to take an extended period of time since these data are distributed at many places. The project will focus its scope to one area at a time. As a starter we will explore the rich area of Saudi geological data, background knowledge, and specific hydrologic investigation queries. Domain-specific experts and historical knowledge will be the main source of background text data. The Saudi Geological Survey (SGS) agency will be the main source of image and text data. One of the investigator is working in a research project investigating Land Slides near Jeddah. He also has been working on the Empty quarter in a previous research project. Other image data will be collected and/or purchased from commercial Internet satellite agencies. At this point in time, the SGS is providing us with data about Al Robh El-Kaly (Empty Quarter). Data about annual precipitation, field region gauges, and aquifer characteristics of rocks at this area are provided. In summary, this project will deliver both a new methodology as well as new results in the area of application. 9 Texture Feature Extraction Texture feature representation A two-dimensional Gabor function and its statistics model Fourier transform 2 2 1 co-occurrence matrices exp 1 x y 2jWx g ( x, y ) 2 2 x y y2 2 probability model x Markov random fields parameters v 2 1 (u W ) 2 transform-based model G(u , v ) exp 2 u2 v 2 Gabor wavelets Feature representation Gabor wavelet transform of an image (PCA 1 region) Wmn ( x, y ) I ( x1 , y1 ) g mn ( x x1 , y y1 )dx1dy1 mean and standard deviation of the magnitude of the coefficients feature vector mn ( x, y ) W mn ( x, y ) dxdy mn ( x, y ) W f 0, 0 0, 0 0,1 0,1 S 1, K 1 S 1, K 1 mn ( x, y ) mn dxdy 2 Category-based Clustering Partition the texture feature space into subspaces in terms of the combined land cover classes Open Water Woody/Emergent Wetlands Grasslands/Herbaceous Pasture/Hay Deciduous/Evergreen Forest Row Crops/Small Grains/Fallow Bare Rock/Sand/Clay Residential/Industrial water/wetlands river/grassland forest/pasture crops/pasture urban/grasslands 10 The above three figures demonstrate the details of figure 1 above. They show the type of interaction between data mining algorithms of classification and cluster with the image processing algorithm of texture feature extraction with background knowledge about vegetation areas. IV-2: AVAILABLE RESOURCES Facilities: The proposed system will use the Oracle database management system and Matlab with its image processing tool box. A powerful development server will be needed. The imagery plug-in accelerator for Oracle will be needed. Four data mining tools will be needed- these are: SAS Oracle data mining tool, CART Salford tool, Discovery DM tool, and Wika DM tool. Data Visualization tool will be needed. III- Estimates of Support Needs Currently we have two students to work on the project. These students have started already working on the implementation of two critical sub-systems. These students are currently taking the Data Mining course CS471 with Dr. Ahmed Sameh. Two more students will be hired as research assistants and programmers in this project. Resource accessing and acquisitions: Oracle is the only resources available at PSU. Other hardware and software need to be acquired (see the budget table below). The estimated cost for both the hardware and software is 20,000 SR. The following tables are extracts from the data provided by SGS to us. 10 11 IV-3: EXPECTED RESULTS/OUTPUTS Deliverables in phase I: Beta Version I + its Benchmark + its Tuning Deliverables in Phase II: Beta Version II + its Benchmark + its Tuning Deliverables in Phase III: Beta Version III + its Benchmark + its Tuning Deliverables in Phase IV: Final Version + User Manual The Saudi Geological Survey in Jeddah as well as the Saudi Military Geological Survey in Riyadh might be interested in acquiring the developed system. The methodology proposed in this project in new, we could apply for a patent after proving its success. 12 The following is the project plan schedule. It represents those different tasks within the research and estimated duration for each. V - REFERENCES 1- NASA http://en.wikipedia.org/wiki/Earth_Observatory 2http://glcf.umiacs.umd.edu/data/landsat/ 3- http://www.bom.gov.au/satellite/ 4- The Saudi Geological Survey Agency http://www.sgs.org.sa/Arabic/Pages/default.aspx 5- The ITSC Algorithm development and Mining (Adam) System http://geoinformatics.itsc.uah.edu/content/algorithm-development-and-mining-adam-system-earth-scienceapplications 6- NASA JPL Diamond Eye System http://ieeexplore.ieee.org/Xplore/login.jsp?url=http%3A%2F%2Fieeexplore.ieee.org%2Fiel5%2F6383%2F1706 2%2F00787650.pdf%3Farnumber%3D787650&authDecision=-203 7- The Insightful VisiMine System http://www.google.com/#hl=en&safe=active&biw=1045&bih=491&q=The+Insightful+VisiMine+System+&aq =f&aqi=m1&aql=&oq=The+Insightful+VisiMine+System+&gs_rfai=&fp=fe2941a855446fc5 VI - ROLE(S) OF THE INVESTIGATOR(S) (Attach a brief CV for each investigator following the format in Appendix A) # Name of Investigator Area of contribution to the project 1 Ahmed Sameh Data Mining 2 Rachid Zantout Image Processing 13 3 Fakhry Kellah 4 Khalid Al-Mustafa 5 Ayman Kassem 6 Mohamed Sultan Image Processing Databases Satellite Systems General Consultant VII - PROJECT SCHEDULE PHASES OF PROJECT IMPLEMENTATION Steps Task System requirements specifications: Sameh, Sid Ahmed, System Architecture : Sultan System Design: Sameh, Rashid Databases Designs: Khalid Matlab Scripts Design: Fakhry Prototyping of critical sub-systems: Rashid, Sameh System Detailed Design: Sameh, Sultan Beta Version Implementation: Sameh, Khalid Testing: Fakhry Building Deployment Environment: Rashid Bench Marking and Collecting Results (First Round): Sameh System Tuning (Based on First Round Results): Khalid, Ali Bench Marking and Collecting Results (Second Round Results): Fakhry System Tuning (Based on Second Round Results): Sameh, Faisal Bench Marking and Collecting Results (Third Round Results): Rachid Version 1 Release Results Documentation and Analysis with the Performance requirements Detailed Code Documentation: Faisal User and Installation Guide (Full How To): Ali Total duration for the proposed project VIII - BUDGET OF THE PROPOSED RESEARCH (Budget in SAR) 14 Duration (Months) See Ganett Chart for detailed timing 24 Month Amount Priority 1 = Max; Amount Requested 2 = Mod; Approved 3 = Low. (SAR) (SAR) Item A. Personnel* (Research Assistant) 48,000 For Official Use 1- Student Ahmed Al-Jabreen 2- Student Kamal Qarawi 3- Student Omar Al-Moughnee 4- Student Amro Al-Munajjed B. Equipment* (List) 10,000 Oracle Server C. Testing and Analysis* (Location/Laboratory) Networking to Clients D. Consumables* (List) 1000 Desk tools E. Travel *(Local/Internat) 10,000 -Travel for Prof. Mohamed Sultan (Michigan/Riyadh) -Travel for Prof. Ayman Kassem (Zahran/Riyadh) F. Software* (List) 10,000 Oracle Accelerator Matlab GIS – ARC –info Tools SAS Data Mining Tools Visualaization Google Earth Oracle 9i Data Mining Tools CART Pro Data Mining Tool 15 Viscovery Data Mining Tool Wika Data Mining Tool G. Other Items* (Itemize) Total Amount Requested (SAR) 79,000 IX- JUSTIFICATION OF BUDGET (Justify each item listed in the budget in the previous section) Item A Justification Four for SR 500 a month for two years Research Assistants B System Development Hardware Oracle Server C For Final deployment Networking to Clients D To be used by the team members Desk tools E For the two outside PSU professors Travel F For system development Software 16 G X - RELEASE TIME FOR RESEARCH TEAM MEMBERS RELEASE TIME FROM TEACHING LOAD # PI CI1 CI2 CI3 CI4 CI5 Time Commitment Team Member (hrs/weeks/terms) Ahmed Sameh 4hrs/week Mohamed Sultan 2hrs/week Rachid Zantout 2hrs/week Fakhry Khella 2hrs/week Khalid El-Moustafa 2hrs/week Ayman Kassem 2hrs/week Teaching Load Max e.g. 1 course FA11 XI - EXTERNAL FUNDING # Source of Funds Amount (SAR) 1 None 2 3 17 Used for …… costs Appendix A: CV Format for Principal Investigator and Co-Investigators (Two pages maximum, material should be related to submitted project) Title and Name: Ahmed Sameh Specialty: Artificial Intelligence Department and College: Computer Science Summary of Experience/Achievements Related to Research Proposal: I’ve published the following publications in the area of this project: 1- Ahmed Sameh, Nazek El-Shazly “C Calibrating Camera Shake Photographs Using Parallel DeConvolution” to appear in the in International Journal of Video & Image Processing and Network Security IJVIPNS- Vol:10 Issue: 03 ISSN: 2077-1207. 2- Ahmed Sameh, “Data Mining Ant Colony for Classifiers” to appear in the International Journal of Basic & Applied Sciences IJBAS- Vol:10 Issue: 03 ISSN: 2077-1223. 3- Ahmed Sameh, Khalid Magdy, "Parallel Ant Colony Optimization" to appear in the International Journal of Research and Reviews in Computer Science (IJRRCS) in June 2010 issue (vol. 1, No. 2) 4- Ahmed Sameh, Nazly El-Shazly, “Removing Camera Shake from Single Photograph Using Parallel DeConvolution”, accepted for presentation and publication at the Computer Graphics, Visualization, Computer Vision and Image Processing – MCCSIS 2010, to be held in Freiburg, Germany, July 27-29, 2010 5- Ahmed Sameh, Khalid magdy, “Data Mining Ant Colony for Classifiers”, accepted for presentation and publication at the 6th Annual International Conference on Computer Science & Information Systems, to be held in Athens, Greece, June 25-28, 2010 6-Essam A. Lotfy, and Mohamed A. Sameh, “Applying Neural Networks in Case-Based Reasoning Adaptation for Cost Assessment of Steel Buildings”, in the ‘Quo Vadis Computational Intelligence Book Chapter, published by ISCI series, Slovakia, August 2000 7- Dalia El-Mansy, Ahmed Sameh, “A Collaborative Inter-Data Grid Strong Semantic Model with Hybrid Namespaces”, Journal of Software (JSW), Academic Publisher, Volume 3, Issue 1, January 2008 8- Ahmed Sameh, and Ayman Kassem, “3D Modeling and Simulation of Lumbar Spine Dynamics”, in the International Journal of Human Factors Modelling and Simulation , Volume IJHFMS-942, 2007 9-Lotfy E.A, Mohamed A. Sameh," Applying Neural Networks in Case-Based Reasoning Adaptation for Cost Assessment of Steel Buildings", International Journal of Computers and Applications, Vol. 24, No. 1, Jan. 2002 10-Adhami Louai, Abdel-Malek Karim, McGowan Dennis, Mohamed A. Sameh, "A Partial Surface/Volume Match for High Accuracy Object Localization", International Journal of Machine Graphics and Vision, vol 10, no. 2, 2001 11- Mohamed A. Sameh and Attia E. Emad, "Parallel 1D and 2D Vector Quantizers Using Kohonen SelfOrganizing Neural Network", in the International Journal of the Neural Computing and Applications, V. (4), no. 2, Springer Verlag, London, 1996 12- Ahmed Sameh, Amgad Madkour, “Intelligent open Spaces: Learning User History Using Neural Network for Future Prediction of Requested Resources”, Proceedings IEEE CSE'08, 11th IEEE International Conference on Computational Science and Engineering, 16-18 July 2008, São Paulo, SP, Brazil. IEEE Computer Society 2008, ISBN 978-0-7695-3193-9 13-Mohamed A. Sameh, "E-Access Custom Webber: A Multi-Protocol Stream Controller", Proceedings of the IADIS International Conference on Applied Computing, Lisbon, Portugal, March 23-26, 2004 14-Mohamed A. Sameh, and Shenouda S., "Tera-Scale High Performance Distributed and Parallel SuperComputing at AUC", Proceedings of the 12th International Conference on Artificial Intelligence, Cairo, Feb. 18-20, 2004 18 15-Kassem Ayman, and Mohamed A. Sameh, “A Fast Technique for modeling and Control of Dynamic System”, Proceedings of the 11th International Conference on Intelligent Systems on Emerging Technologies (ICIS-2002), Boston, July 18-20, 2002 16-Mohamed A. Sameh, and Kaptan Noha, "Anytime Algorithms for Maximal Constraint Satisfaction", Proceedings of the ISCA 14th International Conference on Computer Applications in Industry and Engineering (CAINE' 2001), Nov. 27- 29, at Las Vegas, Nevada, 2001 17-Ghada A. Nasr, and Mohamed A. Sameh, “ Evolution of Recurrent Cascade Correlation Networks with a Distributed Collaborative Species”, Proceedings of the IEEE Symposium on Computations of Evolutionary Computation and Neural Networks, San Antonio, TX, May 2000 18- Mohamed A. Sameh, Botros A. Kamal, "2D and 3D Fractal Rendering and Animation", Proceedings of the Seventh Eurographics Workshop on Computer Animation and Simulation, Aug. 31st- Sept. 2nd, in Poitiers, France, 1996 19- Mohamed A. Sameh, "A Transputer-Based Neural Architecture for Off-line Recognition of Unconstrained Cursive Handwritten Arabic Text", Proceedings of the IASTED International Conference on Modelling, Identification, and Control, held in Innsbruck, Austria, Feb. 20-23, 1995 20- Mohamed A. Sameh, "Integrating Stochastic Grid Maps into Cooperative Mobile Robots", in the Proceedings of the IEEE-IMACS International Conference on Signal Processing, Robotics, and Neural Networks, Lille, France, April 25-27, 1994 21-Mohamed A. Sameh, "Robotics Databases", Proceedings of the 6th International Conference on CAD/CAM, Robotics, and Factories of the Future, England, 1991 22-Mohamed A. Sameh, "A Robust Vision System for three Dimensional Facial Shape Acquisition, Recognition, and Understanding", Proceedings of the 1st Golden West International Conference on Intelligent Systems, Reno, Nevada, 1991 23-Armstrong, W.W., Mohamed A. Sameh, "A Mixed-flow Query Processing Strategy for a Multiprocessor Database Machine", IEEE Proceedings of the 5th International Conference on Distributed Computing Systems, Denver, Colorado, 1985 Sultan’s Short CV: Mohamed I. Sultan Mohamed Sultan, Professor and Chair Office: 269 387-5487; Department of Geosciences Lab: 269 387-5513 Western Michigan University email: [email protected] 1185 Rood Hall Web page: http://www.esrs.wmich.edu/ Kalamazoo, MI 49008-5241 U.S.A. Professional Preparation Washington University, St. Louis, MO Remote Sensing Post Doc. 1985-1988 Washington University, St. Louis, MO Geochemistry Ph.D. 1984 Ain Shams University, Cairo, Egypt Stratigraphy M.Sc. 1978 Ain Shams University, Cairo, Egypt Geology B.Sc. 1974 Appointments 2004Professor and Chair – Department of Geosciences, Western Michigan University 2002-2004 Professor – Department of Geology, University at Buffalo, Amherst, NY. 1996-2002 Project Manager, International Programs – Environmental Research Division, Argonne National Laboratory, Argonne, IL.. 1988-1996 Senior Research Scientist – National Aeronautics and Space Administration (NASA) Earth and Planetary Remote Sensing Facility, Department of Earth and Planetary Sciences, McDonnell Center for the Space Sciences, Washington University, St. Louis, MO. 1984-1988 Research Associate – Department of Earth and Planetary Sciences, Washington University, St. Louis, MO. Honor, Awards 19 Fellow Geological Society America, GSA Annual Meeting, (2009- present) Farouk El-Baz Award for Desert Research, Quaternary Geology and Geomorphology Division, Geological Society of America (1999) Associate Editor – Geological Society America, Bulletin (2004-2007) Research Professor – Department of Geology, University at Buffalo, Amherst, NY (2004-present). Adjunct Associate Professor – Department of Earth and Environmental Sciences, University of Illinois, Chicago, IL (1997-present) Adjunct Full Professor – Department of Geophysics, Cairo University, Giza, Egypt (1996-2007) Adjunct Full Professor – Department of Geology, Ain Shams University, Cairo, Egypt (2000present) Fellow, McDonnell Center for the Space Sciences, Washington University, St. Louis, MO (1988-1996) Current Support Sultan, M., Principal Investigator – Integration of Grace Data with Inferences from Hydrologic Models, Geochemical Data, and Field Data for a Better Understanding of the TimeDependant Water Storage Variability in Large-Scale Aquifers: Case Studies from North Africa (NASA Earth Science Division)(2008-2011) Sultan, M., Principal Investigator – Detailed Studies of Landslides in Jazan Area, Saudi Arabia (Saudi Geological Survey)(2010-2013) Sultan, M., Principal Investigator – The Hydrologic Role of Faults in the Mojave Desert: Fracture Controlled Mountain Front Groundwater Flow, San Bernardino Mountains (Mojave Water Agency)(2009-2011) Sultan, M., Principal Investigator - Assessment and Development of Renewable Groundwater Resources in the Quetta Valley, Pakistan (US State Department)(2007-2010) Sultan, M., Principal Investigator - Assessment and Development of Alternative Water Resources in the Sinai Peninsula, Egypt (NATO Science for Peace and Security)(2007-2011) Sultan, M. Co-P.I - A Proposal to Evaluate the Jet Propulsion Laboratory Mars Exploration Public Engagement Program and Mars Student Imaging Project, (NASA)(2007-2010) Sultan, M., Principle Investigator, The Mesopotamian marshlands from disintegration to restoration (NSF) (2005-2010) Manuscripts (2008-2010) 1. Sultan, M., Metwally, S., Milewski, A, Becker, D., Ahmed, M., Sauck, W., Soliman, F., Sturchio, N., Wagdi, A., Becker, R., and Benjamin, S., 2010, Modern Recharge to the Nubian Aquifer, Sinai Peninsula: Geochemical, Geophysical, and Modeling Constraints, J. Hydrology, (in review) 2. Ahmed,M., Sultan, M., Wahr, J., Yan, E., Milewski, A., Sauck, W., Becker, R., Welton, B., 2010, Integration of GRACE data with traditional datasets for a better understanding of the time-dependent water partitioning in African watersheds, Geology (in review) 3. Sagintayev, Z., Sultan, M., Khan, SD, Khan, SA, Mahmood, K., Yan, E., Milewski, A., Marsala, P., 2010, A Remote Sensing Contribution to Hydrologic Modeling in Arid and Inaccessible Watersheds, Pishin Lora Basin, Pakistan, J. Hydrological Processes (in review) 4. Sultan, M., Fawzy, A., Metwally, S., Becker, R., Milewski, A., Sauck, W., Sturchio, N. C., Mohamed, A.M.M., Wagdy, A., El Alfy, Z., Becker, D., Sagintayev, Z., El Sayed, M., and Welton, B., 2010, Red Sea rifting controls on aquifer distribution: constraints from geophysical, isotopic, and remote sensing data, Geological Society America Bulletin (in press). 5. Becker, R. H., and Sultan, M., 2009, Land Subsidence in the Nile Delta: Inferences from Radar Interferometry, Holocene, vol 19, no. 6, p. 1-6. 6. Becker, R.H., Sultan, M., Boyer, G.L., Twiss, M.R., and Konopko, E., 2009, Mapping cyanbacterial blooms in the Great Lakes using MODIS, Journal Great Lakes Research, v. 35, no 3, p. 447-453. 7. Khan, S. D., Mahmood, K., Sultan, M. I., Khan, A. S., Xiong, Y., Sagintayev, Z., 2010. Trace element geochemistry of groundwater from Quetta Valley, western Pakistan. Journal of Environmental Earth Sciences, 60, 573-582. 8. Makarewicz, J.C., Boyer, G.L., Atkinson, J., Lewis, T.W., Guenther, W., Arnold, M., Becker, R., Sultan, M., Spatial distribution of the cyanotoxin microcystin in the Lake Ontario ecosystem: 20 9. 10. 11. 12. 13. 14. 15. coastal embayments, rivers, nearshore and offshore and upland lakes, Great Lakes (in press). Milewski, A., Sultan, M., Eugene, Y., Abdeldayem, A., and Abdel Gelil, K., 2009, A Remote Sensing Solution for Estimating Runoff and Recharge in Arid Environments, Journal of Hydrology, v. 373, p. 1-14, v. 35, p. 2001-2010. Milewski, A., Sultan, M., Markondiah Jayaprakash, S., Balekai, R., and Becker, R. (2009b), RESDEM, a Tool for Integrating Temporal Remote Sensing Data for use in Hydrogeologic Investigations, Journal of Computers and Geosciences, v. 35, p. 2001-2010. El-Sayed M. Abdelrahman, Essa, K.S., Abo-Ezz, E.R., Sultan, M., Sauck, W.A., and Gharieb, A.G., 2008, New least-squares algorithm for model parameters estimation using self-potential anomalies, Computers and Geosciences, v. 34, p. 1569-15767. Forman, S., Sagintayev, Z., Sultan, M., Smith, S., Kendall, M., Marin, L., and Becker, R., 2008, The migration of parabolic dunes and wetland formation at Cape Cod National Sea Shore, MA: Landscape response to a legacy of human disturbance, Holocene, v. 18, no 5, p. 765-774. Jones, C., Sultan, M., Yan, E., Milewski, A., Hussein, M., Al-Dousari, A., Al-Kaisy, S., Becker, R., 2008, Hydrologic Impacts of Engineering Projects on the Tigris-Euphrates System and its Marshlands, Journal of Hydrology, v. 353, p. 59-75 (doi:10.1016/j.jhydrol.2008.01.029). Sultan, M., Sturchio, N., El Sefry, S., Milewski, A., Becker, R., Nasr, I., 2008, Geochemical, Isotopic, and Modeling Constraints on the Origin and Evolution of the Rub Al Khali Groundwater Aquifer System, Arabian Peninsula, Journal of Hydrology, v. 356, p. 70– 83. Sultan, M., Wagdy, A., Manocha, N., Sauck, W., Abdel Gelil, K., Youssef, A.F., Becker, R., Milewski, A., Jones, C., 2008, An Integrated Approach for Identifying Aquifers in Transcurrent Fault Systems: The Najd Shear System of the Arabian Nubian Shield v. 349(3-4), p 475-488. doi:10.1016/j.jhydrol.2007.11.029. Research Interests The use of holistic and interdisciplinary approaches to characterizing and interpreting the Earth system and its component parts represents one of the most significant advances in Earth and Environmental Science in the past several decades. My research group applies an interdisciplinary research approach that takes advantage of the best available tools to address a wide range of timely and complex geologic and environmental problems. I believe that the adoption of interdisciplinary research approaches leads most directly to the resolution of complex geologic and environmental problems. This approach often requires acquisition of considerable expertise in disciplines other than the area of one’s own primary training, coupled with close interaction with specialists in other fields. I believe that an interdisciplinary researcher should spend his or her efforts to acquire adequate expertise in the various fields and disciplines that are appropriate for addressing the problem under investigation. This acquired multidisciplinary expertise advances collaborations on interdisciplinary projects in many ways. It provides the researcher with a comprehensive understanding of the capabilities and limitations of the various methodologies that are being applied by his co-workers, and it provides a common platform for interactions between researchers coming from different backgrounds. My publication and funding record covers a wide range of disciplines (remote sensing, GIS, hydrology, surface runoff and groundwater flow modeling, geophysics, geochemistry, geochronology and isotope geochemistry, tectonics, Precambrian geology, and Quaternary geology) and attests to the fact that I pursued an interdisciplinary research approach early in my career. Locations of geographic interest include arid and semi-arid areas worldwide where demand for freshwater supplies is on the rise because of increasing populations and limited water supplies. The increasing demand on conventional freshwater supplies in Middle Eastern, Saharan, and the Arabian Peninsula countries could contribute to political instabilities and extreme stresses on the freshwater ecosystem (lakes, ponds, rivers, streams, wetlands, and groundwater). Several of my ongoing projects address the potential influences of natural processes, global change, and regional human activities on hydrologic systems and landforms. Under NSF funding, my collaborators and I are developing and applying an integrated systems approach to assess, monitor, and model the recent and future impacts of 21 changes in the landscape and land cover associated with the major agricultural development projects in the Tigris-Euphrates watershed. Using NSF funding, we applied an interdisciplinary (geochemistry, hydrologic modeling) approach to examine the hydrologic and geomorphologic impacts of the Aswan High Dam. In the upstream, we applied radar interferometric techniques to investigate the impacts of reduced river sediment load, now impounded behind the dam, on land subsidence in the Nile Delta. In the downstream, we constructed a calibrated hydrologic model that showed that increasing sediment thickness at the bottom of Lake Nasser reduces recharge to the underlying aquifer and promotes encroachment of rising Lake Nasser water onto surrounding lands. Using UNDP funding, we developed integrated cost-effective methodologies for the assessment and sustainable management of groundwater resources in arid lands using the Eastern Desert of Egypt as a test site. The success of our applications in the Eastern Desert of Egypt led to three new projects, a NATO-funded project in the Sinai Peninsula, a USAID-funded project in the Quetta region in Pakistan, and a Mojave water agency-funded project in the Lucerne Valley, in southwest USA, where the developed methodologies are being applied. For the latter project we are using hydrologic models, remote sensing, and geophysical methods to evaluate the role of the transcurrent fault systems in channeling groundwater from the mountains to the surrounding lowlands. In the Arabian Peninsula, we demonstrated (using isotopic, geochemical, remote sensing, and GIS) that the Empty Quarter aquifers were largely recharged by precipitation during previous wet climatic periods over the Red Sea Hills, yet are still receiving modern precipitation in the prevailing dry climatic periods such as those being witnessed nowadays. One of the most exciting research areas that we are currently involved in is the applications of GRACE temporal gravity data for the assessment of water storage variability in the African watersheds. Results show that temporal and spatially smoothed (250 km; Gaussian) mass variations are largely controlled by elements of the hydrologic cycle such as runoff, infiltration, and groundwater flow, and that these mass variations are probably modulated, but not obscured by noise as previously thought. If true, our findings suggest that: (1) it is possible to use GRACE to investigate temporal local responses of a much larger suite of (smaller) hydrologic systems (watersheds, lakes, rivers, marshes, etc.) and domains (e.g., source areas, lowlands) within watersheds and sub-basins world-wide, and (2) GRACE data could potentially be used to calibrate land surface models that are being used to drive climatic models and thus provide confidence in the results (e.g., climatic projections) obtained by such models. A comprehensive understanding of Earth systems sciences requires substantial integration among scientific disciplines in terms of concepts, understanding, skills, and problem-solving techniques. The scale of existing global geologic data sets, their extremely uneven documentation, and the relative scarcity of user-friendly access tools are major obstacles to interdisciplinary research. New approaches entail the application of GIS technologies on a global scale, to spatial-temporal integration, visualization, and analysis of geochemical, geophysical, remote sensing, and geodetic data sets. Applications of information technology in geosciences are not restricted to the compilation, visualization, and distribution of geologic data sets, but also in the use of these data sets to apply online dynamic models and simulations for various geologic processes. The application of web-based GIS technologies is especially advantageous in developing countries, where obtaining basic data sets that are relevant to geologic applications, such as digital topography, aerial photography, satellite data, and geologic maps, is often cost prohibitive. We expanded our expertise in the general area of geoinformatics and we are applying the acquired experience to address environmental and tectonic problems of interest. Using the Google Earth Interface, we have now developed a comprehensive web-based GIS (http://www.esrs.wmich.edu/webmap/) that encompasses all the databases we generated and the custom tools that we constructed throughout the years for the distribution, analysis, visualization, and modeling of accumulated data sets. Examples of these databases are the Egyptian database, Saudi database, African GRACE database, and the Mojave database. 22 We developed our research capabilities and expertise in the area of aquatic remote sensing, specifically in limnologic (inland or fresh water) and coastal remote sensing. To expand our research activities in this area, we established a direct downlink and processing system for remote sensing data. This system acquires and examines real-time data over the Great Lakes, where there is great interest, expertise, and ongoing research at UB. The system has been acquired, installed, and is currently fully operational. We have real-time access to the Advanced Very High Resolution Radiometer (AVHRR) L-band sensor data transmitted by National Oceanic and Atmospheric Administration (NOAA) satellites, as well as the Orbview-2 satellite that carries the Sea-viewing Wide Field-of-view Sensor (SeaWiFS) instrument (http://isis.geology.buffalo.edu/UB-receiving-Station-Lakes.htm). Together with scientists from SUNY - College of Environmental Science and Forestry, SUNY- Univ. at Buffalo, SUNY Brockport, Univ. of Vermont, and Univ. of Tennessee we explored the utility of chlorophyll extraction techniques to map the spatial and temporal variations in algal blooms in Lake Erie and Lake Ontario with predictions from a hydrodynamic and particle tracking model to determine transport pathways. The project goal is to develop a system that uses remote sensing to identify the formation of a bloom and can predict the movement of the bloom through modeling. All of the projects that are described above have one thing in common: they impact large sectors of the population in many ways. One research area that I would like to venture into is to complement our existing efforts by bringing on board expertise in the general area of Social Sciences. I can think of many ways in which such expertise can advance our ongoing research activities. One way would be to examine, assess, and model the impacts of our findings on impacted populations. For example, we could assess population migration patterns that are related to development of the major engineering projects in the Tigris Euphrates watershed. Social scientists could also provide guidelines as to how our methodologies and approaches can be optimized to factor in the social aspects that will eventually dictate whether our developed methodologies will be practical enough or appealing enough to be adopted/implemented. Breaching the gap between physical and social sciences is becoming more and more a necessity for the success of many of the applied projects today and many of the funding agencies are realizing the importance of such approach. Physical scientists from various disciplines have done quite well working together to address complex environmental problems. Such integrated research will benefit from expanding existing models to encompass social disciplines as well. Appendix B: Evaluations and Approvals COLLEGE REVIEW COMMITTEE Evaluation and Recommendation Excellent Item/ Evaluation Research methodology Research objectives Research originality Research contribution Research applicability and relevance 23 Very Good Good Weak Overall evaluation Recommendations of College Committee Approved Amount of Budget Approved by College Committee: Disapproved (SAR) Chair College Committee - Title and Full Name: Signature: Date: Recommendations of the College Council / Approved / Disapproved Dean of the College Council - Title and Full Name Signature: Date: / / PSU INSTITUTIONAL RESEARCH COMMITTEE (IRC) Recommendation Recommendation of the PSU IRC Approved Disapproved Chair IRC Committee - Title and Full Name: Signature: Date: 24 / / PSU EXTERNAL REVIEW PANEL FOR RESEARCH PROPOSALS Recommendation Recommendation of the Eternal Review Committee. Approved: Amount of grant approved: Disapproved: Postponed: Directed to: Chair of External Review Panel - Title and Full Name: Signature: ( SAR) Date: Recommendation of University Council / / Approved Signature: Date: 25 Disapproved / /