IMPROVING HIGH RESOLUTION (M SCALE) MAPPING OF SNOW COVERED AREAS IN COMPLEX FORESTED TERRAIN IS CRUCIAL TO UNDERSTANDING CHANGES AND RELATED RESPONSES OF SPECIES AND WATER SYSTEMS TO CLIMATE CHANGE. PLANET LABS INC. (PLANET) IS A PROMISING NEW SOURCE OF COMMERCIAL HIGH-RESOLUTION IMAGERY THAT CAN BE USED IN ENVIRONMENTAL SCIENCE AS IT HAS BOTH HIGH SPATIAL (0.7-3.0 M) AND TEMPORAL (1-2 DAY) RESOLUTION. HOWEVER ITS IMMEDIATE UTILITY WITH RESPECT TO INFERRING SNOW COVER IS MORE RESTRICTIVE DUE TO THE LIMITATIONS IN THE NUMBER AND BANDWIDTH OF THE NEAR-INFRARED (NIR) BAND WHICH MAKES DISTINGUISHING SNOW PIXELS FROM OTHER LAND COVER PIXELS CHALLENGING USING A TRADITIONAL RADIOMETRIC INDEX (SUCH AS THE NORMALIZED DIFFERENCE SNOW INDEX NDSI) AND THEREFORE REQUIRES AN ALTERNATIVE APPROACH. WE WILL EXTEND A MACHINE LEARNING FRAMEWORK BASED ON CONVOLUTIONAL NEURAL NETWORKS TO IMPROVE SNOW COVER MAPPING IN COMPLEX TERRAIN AND FORESTED REGIONS IN FOREST GAPS AND BETWEEN SPARSE TREES. WE WILL COUPLE GROUND AND AIRBORNE-DERIVED SNOW OBSERVATIONS WITH PLANET IMAGERY IN DIFFERENT MOUNTAIN SYSTEMS IN WASHINGTON CALIFORNIA AND COLORADO USA. THESE SITES ARE IDEAL CANDIDATES FOR OUR ANALYSIS AS THEY DIFFER IN CLIMATE AND TOPOGRAPHIC FEATURES AND ARE SITES WHERE GROUND AND AIRBORNE SNOW OBSERVATIONS AT HIGH RESOLUTION (3M) HAVE BEEN COLLECTED BY THE NASA AIRBORNE SNOW OBSERVATORY (ASO) AND SNOWEX MISSIONS. WHILE BASIC WORKFLOWS WILL BE DEVELOPED USING PLANET DATA THIS PROPOSAL WILL BE CONSIDERING DATA FROM OTHER SMALLSAT PROVIDERS. THE AVAILABILITY OF HIGH RESOLUTION SNOW MAPS CAN IMPROVE WATER FOREST AND ECOSYSTEMS MANAGEMENT INFORM CORRECTIONS FOR COARSER RESOLUTION SNOW PRODUCTS AND ALBEDO ESTIMATES ACROSS FORESTED REGIONS.