Improving the accuracy of models to map alpine grassland above‐ground biomass using Google earth engine

Abstract

Accurate modelling and mapping of alpine grassland aboveground biomass (AGB) are crucial for pastoral agriculture planning and management on the Qinghai Tibet Plateau (QTP). This study assessed the effectiveness of four popular models (traditional multiple linear regression (MLR), support vector machine (SVM), artificial neural network (ANN), and deep neural network (DNN)) with various input combinations (geospatial variables [GV], vegetation types [VT], field measurements [FM], meteorological variables [MV] and observation time [OT]) for AGB estimation based on a new framework for AGB modelling and mapping using Google Earth Engine. The results showed that the input feature of GV had a poor performance in AGB estimation (0.121 < R2 < 0.591). FM improved the accuracy the most when incorporated with GV (0.815 < R2 < 0.833). Although MV, VT and OT improved the accuracy (R2) only by 0.112–0.216 with an importance rank order of MV > VT > OT for machine learning models, their outputs could be used to map AGB. Grass AGB was less accurately predicted than shrub AGB, but the pooling of both VTs improved estimation accuracy (R2) by 0.171–0.269. The performance of the models followed the ranked order of DNN > ANN > SVM > MLR. DNN had the highest accuracy (R2 = 0.818) using all non‐field measured variables (excluding FM) as the inputs, and it was successfully applied to a new dataset (not associated with the data used in the training and testing) with a R2 of 0.676. This study presents an effective and operational framework for modelling and mapping grassland AGB. Accordingly, it provides the scientific foundations to determine of sustainable grazing carrying capacity in alpine grasslands.

Grassland, forage, and turfgrass science in China

“…In recent years, the number of papers published in Grass and Forage Science from China has seen an increase. For example, two other Chinese papers were published earlier in 2023 (Shi et al, 2023 andXue et al, 2023), while only eight appeared in the period between 2019 and 2022 (Dai et al, 2019;Liu et al, 2019;Wang et al, 2019;Yuan et al, 2019;Gao et al, 2020;Wu et al, 2021;Kang et al, 2022;Li et al, 2022). In view of the work ongoing in China, we expect this trend will continue in the coming years.…”