Abstract
Rice is an important food resource, and the demand for rice has increased as population has expanded. Therefore, accurate paddy rice classification and monitoring are necessary to identify and forecast rice production. Satellite data have been often used to produce paddy rice maps with more frequent update cycle (e.g., every year) than field surveys. Many satellite data, including both optical and SAR sensor data (e.g., Landsat, MODIS, and ALOS PALSAR), have been employed to classify paddy rice. In the present study, time series data from Landsat, RADARSAT-1, and ALOS PALSAR satellite sensors were synergistically used to classify paddy rice through machine learning approaches over two different climate regions (sites A and B). Six schemes considering the composition of various combinations of input data by sensor and collection date were evaluated. Scheme 6 that fused optical and SAR sensor time series data at the decision level yielded the highest accuracy (98.67% for site A and 93.87% for site B). Performance of paddy rice classification was better in site A than site B, which consists of heterogeneous land cover and has low data availability due to a high cloud cover rate. This study also proposed Paddy Rice Mapping Index (PMI) considering spectral and phenological characteristics of paddy rice. PMI represented well the spatial distribution of paddy rice in both regions. Google Earth Engine was adopted to produce paddy rice maps over larger areas using the proposed PMI-based approach.
Highlights
Rice is one of the important food resources for most of the world’s population, especially those in Asia [1,2]
This study proposed Paddy rice Mapping Index (PMI) when considering the spectral and temporal characteristics of paddy rice that can be applied to areas that have different climatic and environmental characteristics
This study evaluated six schemes to identify the improvement of classification performance through the investigation of the characteristics of study areas, classifiers, and fusion of multi-sensor time series data
Summary
Rice is one of the important food resources for most of the world’s population, especially those in Asia [1,2]. Dong et al [17] divided paddy rice mapping studies into four categories, using (1) reflectance data and statistical approaches, (2) vegetation index (VI) and enhanced statistical approaches, (3) temporal analysis approaches with VI or RADAR data, and (4) phenology-based approaches They discussed the current challenges and opportunities in future paddy rice mapping: to improve algorithms with the development of land cover classification approaches, to improve data acquisition capacity with high spatial resolution (~30 m) such as combined Landsat and Sentinel-2 data, and to improve computing capacity such as using Google Earth Engine. We conducted paddy rice classification through fusion of optical sensor and SAR time series data using two machine learning approaches, RF and SVM. This study proposed Paddy rice Mapping Index (PMI) when considering the spectral and temporal characteristics of paddy rice that can be applied to areas that have different climatic and environmental characteristics
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have