Estimation of leaf area index and above-ground biomass in soybean canopy using Sentinel-1 & 2, and Landsat images
Abstract
Information on crop development and health during the growing season can be valuable for optimizing crop production. Spatially continuous high-resolution information of crop development could provide producers with decision-aid information for efficient side-dress fertilizer applications , irrigation scheduling, disease and weed control, as well as yield forecasting at early stage. In this study, we demonstrate the potential of integrating synthetic aperture radar (SAR, Sentinel-1) and optical remote sensing (Landsat-8 and Sentinel-2) data to monitor soybean growth status in Mississippi state, USA. Leaf area index (LAI) and aboveground biomass (AGB) were used as indicators of soybean growth status under varying climate and human activities. We assessed the seasonal dynamics of LAI and AGB using data of Sentinel-1 (S1), Sentinel-2 (S2) and Landsat-8 (LC8) data, both individually and integrally. Three widely used algorithms were applied: Multiple Linear Regression (MLR), Support Vector Machine (SVM), and Random Forest (RF). Results indicated that the integration of LC8 and S2 data provided sufficient information to capture seasonal dynamics of soybean at 10-30-m spatial resolution. The remote sensing LAI and AGB models developed from ground measurements in 2016 (2017) reasonably predicted the seasonal dynamics and spatial heterogeneity of LAI and AGB in 2017 (2018). By comparison, the integration of S1, S2, and LC8 has the potential to improve estimation accuracy of LAI and AGB approximately 35% relative to the performance of S1 at low vegetation cover (LAI<4.62 m2/m2, AGB < 277.3 g/m2) and optical data of LC8 and S2 at high vegetation cover (LAI > 4.62 m2/m2, AGB> 277.3g/m2). These results demonstrated that application of combining S1, LC8, and S2 monitoring data couple with algorithms of MLR, SVM and RF could provide timely and accurate decision support information for crop management.
- Publication:
-
AGU Fall Meeting Abstracts
- Pub Date:
- December 2019
- Bibcode:
- 2019AGUFMGC23H1442W
- Keywords:
-
- 0402 Agricultural systems;
- BIOGEOSCIENCES;
- 1632 Land cover change;
- GLOBAL CHANGE;
- 1640 Remote sensing;
- GLOBAL CHANGE;
- 6309 Decision making under uncertainty;
- POLICY SCIENCES & PUBLIC ISSUES