A Machine Learning Method for Predicting Vegetation Indices in China

Abstract

To forecast the terrestrial carbon cycle and monitor food security, vegetation growth must be accurately predicted; however, current process-based ecosystem and crop-growth models are limited in their effectiveness. This study developed a machine learning model using the extreme gradient boosting method to predict vegetation growth throughout the growing season in China from 2001 to 2018. The model used satellite-derived vegetation data for the first month of each growing season, CO2 concentration, and several meteorological factors as data sources for the explanatory variables. Results showed that the model could reproduce the spatiotemporal distribution of vegetation growth as represented by the satellite-derived normalized difference vegetation index (NDVI). The predictive error for the growing season NDVI was less than 5% for more than 98% of vegetated areas in China; the model represented seasonal variations in NDVI well. The coefficient of determination (R2) between the monthly observed and predicted NDVI was 0.83, and more than 69% of vegetated areas had an R2 > 0.8. The effectiveness of the model was examined for a severe drought year (2009), and results showed that the model could reproduce the spatiotemporal distribution of NDVI even under extreme conditions. This model provides an alternative method for predicting vegetation growth and has great potential for monitoring vegetation dynamics and crop growth.

Quantifying the Impacts of the 2020 Flood on Crop Production and Food Security in the Middle Reaches of the Yangtze River, China

“…Food security and related issues are always the PRC's highest priority and are among the most sensitive of topics. Recently, several techniques have been developed to map cropland patterns and dynamics from RS observations, including traditional satellite-based LULC mapping and UAV imagery applications [49][50][51][52][53]. These studies focus on the damage assessment of high-value crops in smaller areas.…”

Can remote sensing enable a Biomass Climate Adaptation Index for agricultural systems?

“…The Elman recurrent neural network model (ERNN) has been used for short-term NDVI index forecasting (Stepchenko and Chizhov, 2015). Machine learning model-based extreme gradient boosting method has been used to predict vegetation growth represented by NDVI throughout the growing season from 2001 to 2018 in China (Li et al, 2021). By assessing NDVI, leaf area index (LAI) and normalized difference water index (NDWI) derived from Landsat 8 surface reflectance, grape yield estimations were made using artificial neural network (ANN) based machine learning and regression analysis (Arab et al, 2021).…”

“…Despite the availability of numerous deep machine learning models, their prediction accuracy may vary greatly when used in biomass-based adaptation indexes. For instance, CNN and RF display good performance in vegetation growth predictions from NDVI (Ayhan et al, 2020;Li et al, 2021;Mishra and Shahi, 2021;Ferchichi et al, 2022). The performance of machine learning models can be evaluated through a range of approaches, including Root Mean Square Error (RMSE), coefficient of determinates (R 2) , Pearson correlation (R), and structural similarity (SSIM), which have been used by Rhif et al (2020), Ahmad et al (2020b), Arab et al (2021), Htitiou et al (2021), Mishra andShahi (2021), andRoy (2021).…”

Data-Driven Artificial Intelligence Model of Meteorological Elements Influence on Vegetation Coverage in North China

“…Artificial intelligence (AI) is a method to explore the relationship between independent and dependent variables of a system according to the existing data, so that the model can make the most accurate estimation possible when the output is unknown [24,25]. Several algorithms, such as random forest regression, regression trees, and support vector regression, are applied to prediction of vegetation change [22,23,26]. SVM is a typical binary classification method which has the advantages of solving high-dimensional problems, dealing with nonlinear problems, and low generalization error rate.…”