Not listed
COLLABORATIVE RESEARCH: PACSP TOOLS: EPICS: EXPLAINABLE AI DRIVEN INDIVIDUAL PHOTO-IDENTIFICATION AND TRACKING FOR COST-EFFECTIVE CONSERVATION STUDY -MARINE ANIMAL TRACKING, AT BOTH INDIVIDUAL AND GROUP LEVELS, IS CRUCIAL FOR WILDLIFE CONSERVATION. IT PROVIDES ESSENTIAL INFORMATION AND INVALUABLE INSIGHTS INTO POPULATION DYNAMICS, HEALTH, RISKS, AND VULNERABILITY, ALL OF WHICH HELP SHAPE CONSERVATION POLICIES, MANAGEMENT DECISIONS AND STRATEGIES. TRADITIONAL TRACKING METHODS FACE SIGNIFICANT CHALLENGES IN BALANCING COST AND PRECISION. THEY EITHER REQUIRE ATTACHING TRANSMITTERS TO ANIMALS THAT COMMUNICATE WITH RADIO RECEIVERS OR SATELLITES (HIGH ACCURACY BUT EXPENSIVE AND INVASIVE) OR RELY ON MANUALLY PRODUCED SKETCHES FROM PHOTOS OF DISTINCTIVE FEATURES SUCH AS SCARS (LOW ACCURACY AND LABOR-INTENSIVE). THE OVERARCHING GOAL OF THIS PROJECT IS TO OPTIMIZE THIS COST-PRECISION TRADE-OFF BY DESIGNING AND DELIVERING AN ARTIFICIAL INTELLIGENCE (AI)-DRIVEN SYSTEM FOR INDIVIDUAL PHOTO-IDENTIFICATION AND TRACKING IN CONSERVATION STUDIES OF FLORIDA MANATEES, A THREATENED SPECIES. THE SYSTEM AIMS TO STREAMLINE THE CREATION, MAINTENANCE, QUERY, AND BEHAVIOR ANALYSIS OF MANATEES USING PHOTO-IDENTIFICATION. THIS PROJECT WILL TRAIN SEVERAL GRADUATE STUDENTS, AND WILL ADVANCE COLLABORATION BETWEEN AI RESEARCHERS AND CONSERVATION SCIENTISTS. IN ORDER TO BRING TRANSFORMATIVE ADVANCEMENTS TO CURRENT CONSERVATION CAPABILITIES, EMPHASIZING COST-EFFECTIVE, EVIDENCE-BASED CONSERVATION PLANNING, THE PROJECT WILL 1) DEVELOP NEW ALGORITHMS GROUNDED IN EXPLAINABLE AI TO IDENTIFY AND TRACK INDIVIDUAL MANATEES BY THEIR DISTINCTIVE FEATURES, SUCH AS SCARS AND MARKERS, WHICH SERVE AS INTERPRETABLE EVIDENCE FOR TRACKING; 2) SUPPORT LONG-RANGE SPATIO-TEMPORAL TRACKING BY REPRESENTING EACH ANIMAL AS A SERIES OF SKETCH IMAGES THROUGHOUT THEIR LIFESPAN, ANNOTATED WITH TIMESTAMPS, GEOGRAPHIC INFORMATION, AND METADATA ON LIFE ENCOUNTERS; AND 3) CRAFT A FRAMEWORK FOR REGION-BASED CONSERVATION RESOURCE PLANNING AND MANAGEMENT THAT MODELS EVOLVING PATTERNS IN LOCAL REGIONS, INCLUDING BOTH NATURAL AND HUMAN-CAUSED DISTURBANCES, TO ASSESS HOW LOCAL ANIMAL POPULATIONS REACT TO THESE REGIONAL CHANGES. THE COLLABORATIVE RESEARCH TEAM WILL ALSO EXTEND APPROACHES TO ADDITIONAL THREATENED OR ENDANGERED MARINE SPECIES (SEA TURTLES, WHALES, RAYS). THIS PROJECT WILL HAVE A LASTING IMPACT ON THE RESEARCH COMMUNITY AND EDUCATION SECTORS BY HIGHLIGHTING CRITICAL NEEDS AND SHOWCASING VIABLE DESIGN IDEAS IN BOTH CONSERVATION AND COMPUTER SCIENCE, AND IN THEIR NEXUS. THIS PROJECT IS JOINTLY FUNDED BY THE DIVISION OF ENVIRONMENTAL BIOLOGY AND INTEGRATIVE ORGANISMAL SYSTEMS THROUGH THE PARTNERSHIP TO ADVANCE CONSERVATION SCIENCE AND PRACTICE PROGRAM. THIS AWARD REFLECTS NSF'S STATUTORY MISSION AND HAS BEEN DEEMED WORTHY OF SUPPORT THROUGH EVALUATION USING THE FOUNDATION'S INTELLECTUAL MERIT AND BROADER IMPACTS REVIEW CRITERIA.
$0 10/25/24 Not listed
COLLABORATIVE RESEARCH: PACSP TOOLS: EPICS: EXPLAINABLE AI DRIVEN INDIVIDUAL PHOTO-IDENTIFICATION AND TRACKING FOR COST-EFFECTIVE CONSERVATION STUDY -MARINE ANIMAL TRACKING, AT BOTH INDIVIDUAL AND GROUP LEVELS, IS CRUCIAL FOR WILDLIFE CONSERVATION. IT PROVIDES ESSENTIAL INFORMATION AND INVALUABLE INSIGHTS INTO POPULATION DYNAMICS, HEALTH, RISKS, AND VULNERABILITY, ALL OF WHICH HELP SHAPE CONSERVATION POLICIES, MANAGEMENT DECISIONS AND STRATEGIES. TRADITIONAL TRACKING METHODS FACE SIGNIFICANT CHALLENGES IN BALANCING COST AND PRECISION. THEY EITHER REQUIRE ATTACHING TRANSMITTERS TO ANIMALS THAT COMMUNICATE WITH RADIO RECEIVERS OR SATELLITES (HIGH ACCURACY BUT EXPENSIVE AND INVASIVE) OR RELY ON MANUALLY PRODUCED SKETCHES FROM PHOTOS OF DISTINCTIVE FEATURES SUCH AS SCARS (LOW ACCURACY AND LABOR-INTENSIVE). THE OVERARCHING GOAL OF THIS PROJECT IS TO OPTIMIZE THIS COST-PRECISION TRADE-OFF BY DESIGNING AND DELIVERING AN ARTIFICIAL INTELLIGENCE (AI)-DRIVEN SYSTEM FOR INDIVIDUAL PHOTO-IDENTIFICATION AND TRACKING IN CONSERVATION STUDIES OF FLORIDA MANATEES, A THREATENED SPECIES. THE SYSTEM AIMS TO STREAMLINE THE CREATION, MAINTENANCE, QUERY, AND BEHAVIOR ANALYSIS OF MANATEES USING PHOTO-IDENTIFICATION. THIS PROJECT WILL TRAIN SEVERAL GRADUATE STUDENTS, AND WILL ADVANCE COLLABORATION BETWEEN AI RESEARCHERS AND CONSERVATION SCIENTISTS. IN ORDER TO BRING TRANSFORMATIVE ADVANCEMENTS TO CURRENT CONSERVATION CAPABILITIES, EMPHASIZING COST-EFFECTIVE, EVIDENCE-BASED CONSERVATION PLANNING, THE PROJECT WILL 1) DEVELOP NEW ALGORITHMS GROUNDED IN EXPLAINABLE AI TO IDENTIFY AND TRACK INDIVIDUAL MANATEES BY THEIR DISTINCTIVE FEATURES, SUCH AS SCARS AND MARKERS, WHICH SERVE AS INTERPRETABLE EVIDENCE FOR TRACKING; 2) SUPPORT LONG-RANGE SPATIO-TEMPORAL TRACKING BY REPRESENTING EACH ANIMAL AS A SERIES OF SKETCH IMAGES THROUGHOUT THEIR LIFESPAN, ANNOTATED WITH TIMESTAMPS, GEOGRAPHIC INFORMATION, AND METADATA ON LIFE ENCOUNTERS; AND 3) CRAFT A FRAMEWORK FOR REGION-BASED CONSERVATION RESOURCE PLANNING AND MANAGEMENT THAT MODELS EVOLVING PATTERNS IN LOCAL REGIONS, INCLUDING BOTH NATURAL AND HUMAN-CAUSED DISTURBANCES, TO ASSESS HOW LOCAL ANIMAL POPULATIONS REACT TO THESE REGIONAL CHANGES. THE COLLABORATIVE RESEARCH TEAM WILL ALSO EXTEND APPROACHES TO ADDITIONAL THREATENED OR ENDANGERED MARINE SPECIES (SEA TURTLES, WHALES, RAYS). THIS PROJECT WILL HAVE A LASTING IMPACT ON THE RESEARCH COMMUNITY AND EDUCATION SECTORS BY HIGHLIGHTING CRITICAL NEEDS AND SHOWCASING VIABLE DESIGN IDEAS IN BOTH CONSERVATION AND COMPUTER SCIENCE, AND IN THEIR NEXUS. THIS PROJECT IS JOINTLY FUNDED BY THE DIVISION OF ENVIRONMENTAL BIOLOGY AND INTEGRATIVE ORGANISMAL SYSTEMS THROUGH THE PARTNERSHIP TO ADVANCE CONSERVATION SCIENCE AND PRACTICE PROGRAM. THIS AWARD REFLECTS NSF'S STATUTORY MISSION AND HAS BEEN DEEMED WORTHY OF SUPPORT THROUGH EVALUATION USING THE FOUNDATION'S INTELLECTUAL MERIT AND BROADER IMPACTS REVIEW CRITERIA.- SUBAWARDS ARE NOT PLANNED FOR THIS AWARD.
$269.7k 9/6/24