Modeling Alpine Grassland Above Ground Biomass Based on Remote Sensing Data and Machine Learning Algorithm: A Case Study in East of the Tibetan Plateau, China

Abstract

Effective and accurate assessment of grassland above-ground biomass (AGB) especially via remote sensing (RS), is crucial for forage-livestock balance and ecological environment protection of alpine grasslands. Because of complexity and extensive spatial distribution of natural grassland resources, the RS estimation models based on moderate resolution imaging spectroradiometer (MODIS) data exhibited low accuracy and poor stability. In this study, various methods for estimating the AGB of alpine grassland vegetation using MODIS vegetation indices were evaluated by combining with meteorology, soil, topography geography and in situ measured AGB data (during grassland growing season from 2011 to 2016) in Gannan region. Results show that (1) five out of ten factors (elevation, slope, aspect, topographic position, temperature, precipitation and the concentration of clay and sand in the soil) exert significant effects on grassland AGB, with R 2 0.04~0.39, and RMSE 859.68 kg/ha ~ 1075.09 kg/ha, respectively; (2) the accuracy and stability of AGB estimation model can be improved by constructing multivariate models, especially using multivariate non-parameter models; (3) the optimum estimation model is constructed on the basis of random forest algorithm (RF). Compared with univariate/multivariate parameter models, RMSE of RF model decreased 26.45 %-44.27 %. Meanwhile, RF models can explain 89.41 % variation in AGB during grass growing season. This study presented a more suitable RS inversion model integrated MODIS vegetation indices and other effect factors. Besides, the accuracy based on MODIS data were greatly improved. Thus, our study provides a scientific basis for effective and accurate estimating alpine grassland AGB.

Quantitative Analysis of the Research Trends and Areas in Grassland Remote Sensing: A Scientometrics Analysis of Web of Science from 1980 to 2020

“…Studies related to the water surface area of lakes on the steppe [49] were mainly concerned with soil quality [50][51][52], soil function, and soil organic matter [53]. The engineering electrical electronic area related to the use of yield estimation in grasslands using remote sensing products [17,54,55], modeling based on remote sensing data [8], and machine learning methods or advanced algorithms [9,56,57]. The entomology area was mainly concerned with the relationship between the density of different species and grassland ecosystems [58], for instance, arthropods [59], thrips species [60], spiders and Auchenorrhyncha assemblages [61], flies [62], black imported fire ants and other insects [63], and biological control insects [64,65].…”

“…The habitat is fragile, the terrain is complex, and the grassland ecological environment is heavily degraded [4]. GRS research provides important support for scientific management and dynamic monitoring [56,67,68].…”

“…The change in remote sensing techniques, from aerial remote sensing to satellite remote sensing [12,22], has achieved a significant advance in the continuity of research scales and temporal and spatial integrity, and the monitoring accuracy and timeliness have improved considerably [28]. For the model inversion method [18,56], many explorations have been carried out in terms of empirical statistical methods (e.g., image processing algorithm), physical model methods (e.g., radiative transfer model, geometrical optics model), and data modeling methods (e.g., data-intensive scientific discovery, space earth observation data model) [14]. In particular, the widespread application of model inversion methods, such as the vegetation index (NDVI) [8,48,52,67] and leaf area index (LAI) [58,[68][69][70], has greatly promoted the development of grassland quantitative remote sensing [71][72][73][74].…”

“…From 1980 to 2020, the field of GRS monitoring, and monitoring of objects, gradually expanded. The application of the field is no longer limited to monitoring grassland resources [8,56]. Grassland utilization, land cover change, and qualitative environmental monitoring have gradually expanded to quantitative monitoring of water, soil, and ecological parameters.…”

“…Classification: From 1980 to 2020, the selection of data sources has undergone drastic changes. Due to the development of machine learning technology [20,56], the applications of GRS research have greatly increased. GRS research data sources have developed from a single type of multispectral data (such as MODIS and Landsat TM) to the currently widely used hyperspectral data [12,87], multi-angle data [8,17,74], laser radar data [18], high-resolution data [88], unmanned aerial vehicle (UAV) data [89], and multi-source data.…”