Enhancing Grazing land Analysis through Integrated Earth Observation and Machine Learning

Grazing lands play an important role in providing food for livestock and carbon sequestration. Accurate assessment of grazing land biomass is essential for effective management. However, it is challenging to estimate biomass and other relevant characteristics of grazing lands due to complex environmental factors. This study enhances grazing land analysis for 2021 year in the United States by integrating Earth observation data and machine learning techniques. Unsupervised clustering algorithms were employed based on key environmental factors affecting grazing lands, including precipitation, elevation, land surface temperature, and vegetation cover. Using the Google Earth Engine platform, data from the National Land Cover Database, MODIS, SRTM, and GPM were utilized as inputs for unsupervised clustering. The environmental factors of each cluster were examined for their correlation with reference biomass from the Rangeland Analysis Platform. The results highlight the diversity of environmental conditions within grazing lands and underscore the importance of considering multiple environmental factors for reliable biomass estimation. This research contributes to developing reliable biomass estimation models over a wide range of grazing lands, enhancing the sustainable management of these vital ecosystems.