资源环境科技发展态势分析平台

Rangelands are a key global resource, providing a broad range of ecological services and economic benefits. California's predominantly annual rangelands cover ~12% of the state's land area, and the forage production is highly heterogeneous, making balancing economic (grazing), conservation (habitat) and environmental (erosion/water quality) objectives a big challenge. Herein, we examined how climate and environmental factors regulate annual grassland forage production spatially across the state and among four ecoregions using machine learning models. We estimated annual forage production at 30 m resolution over a 14 year period (2004–2017) using satellite images and data fusion techniques. Our satellite-based estimation agreed well with independent field measurements, with a R² of 0.83 and RMSE of 682 kg ha⁻¹. Forage production (14 year average) showed large spatial variability (2940 ± 934 kg ha^-1 yr^-1; CV = 35%) across the study area. The gradient boosted regression tree with 11 feature variables explained 67% of the variability in forage production across the state. Precipitation amount, especially in November (germination) and April (rapid growth), was found as the dominant driver for spatial variation in forage production, especially in drier ecoregions and during drier years. Seasonal distribution of precipitation and minimum air temperature showed a relatively stronger control on forage production in wetter regions and during wet years. Additionally, solar energy became more important in wetter ecoregions. Drought reduced forage production from the long-term mean, i.e. a 33% ± 19% decrease in production (2397 ± 926 kg ha^-1yr^-1; CV = 38%) resulting from a 29% ± 5% decrease in precipitation. The machine learning based spatial analysis using 'big data' provided insights on impacts of climate and environmental factors on forage production variation at various scales. This study demonstrates a cost-effective approach for rapid mapping and assessment of annual forage production with the potential for near real-time application.