Evaluation of machine learning models for rice dry biomass estimation and mapping using quad-source optical imagery
Several machine learning regression models have been advanced for the estimation of crop biophysical parameters with optical satellite imagery. However, literature on the comparative performances of such models is still limited in range and scope, especially under multiple data sources, despite the...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2020-08-01
|
| Series: | GIScience & Remote Sensing |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/15481603.2020.1799546 |
| _version_ | 1797679110690963456 |
|---|---|
| author | Lamin R. Mansaray Adam Sheka Kanu Lingbo Yang Jingfeng Huang Fumin Wang |
| author_facet | Lamin R. Mansaray Adam Sheka Kanu Lingbo Yang Jingfeng Huang Fumin Wang |
| author_sort | Lamin R. Mansaray |
| collection | DOAJ |
| description | Several machine learning regression models have been advanced for the estimation of crop biophysical parameters with optical satellite imagery. However, literature on the comparative performances of such models is still limited in range and scope, especially under multiple data sources, despite the potential of multi-source imagery to improving crop monitoring in cloudy areas. To fill in this knowledge gap, this study explored the synergistic use of Landsat-8, Sentinel-2A, China’s environment and disaster monitoring and forecasting satellites (HJ-1 A and B) and Gaofen-1 (GF-1) data to evaluate four machine learning regression models that include Random Forest (RF), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), and Gradient Boosting Decision Tree (GBDT), for rice dry biomass estimation and mapping. Taking a major rice cultivation area in southeast China as case study during the 2016 and 2017 growing seasons, a cross-calibrated time series of the Enhanced Vegetation Index (EVI) was obtained from the quad-source optical imagery and on which the aforementioned models were applied, respectively. Results indicate that in the before rice heading scenario, the most accurate dry biomass estimates were obtained by the GBDT model (R2 of 0.82 and RMSE of 191.8 g/m2) followed by the RF model (R2 of 0.79 and RMSE of 197.8 g/m2). After heading, the k-NN model performed best (R2 of 0.43 and RMSE of 452.1 g/m2) followed by the RF model (R2 of 0.42 and RMSE of 464.7 g/m2). Whist the k-NN model performed least in the before heading scenario, SVM performed least in the after heading scenario. These findings may suggest that machine learning regression models based on an ensemble of decision trees (RF and GBDT) are more suitable for the estimation of rice dry biomass, at least with optical satellite imagery. Studies that would extend the evaluation of these machine learning models, to other parameters like leaf area index, and to microwave imagery, are hereby recommended. |
| first_indexed | 2024-03-11T23:08:38Z |
| format | Article |
| id | doaj.art-a32e7297e7be4969b449f31e5d2a8865 |
| institution | Directory Open Access Journal |
| issn | 1548-1603 1943-7226 |
| language | English |
| last_indexed | 2024-03-11T23:08:38Z |
| publishDate | 2020-08-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | GIScience & Remote Sensing |
| spelling | doaj.art-a32e7297e7be4969b449f31e5d2a88652023-09-21T12:34:16ZengTaylor & Francis GroupGIScience & Remote Sensing1548-16031943-72262020-08-0157678579610.1080/15481603.2020.17995461799546Evaluation of machine learning models for rice dry biomass estimation and mapping using quad-source optical imageryLamin R. Mansaray0Adam Sheka Kanu1Lingbo Yang2Jingfeng Huang3Fumin Wang4Zhejiang UniversitySierra Leone Agricultural Research Institute (SLARI)Zhejiang UniversityZhejiang UniversityZhejiang UniversitySeveral machine learning regression models have been advanced for the estimation of crop biophysical parameters with optical satellite imagery. However, literature on the comparative performances of such models is still limited in range and scope, especially under multiple data sources, despite the potential of multi-source imagery to improving crop monitoring in cloudy areas. To fill in this knowledge gap, this study explored the synergistic use of Landsat-8, Sentinel-2A, China’s environment and disaster monitoring and forecasting satellites (HJ-1 A and B) and Gaofen-1 (GF-1) data to evaluate four machine learning regression models that include Random Forest (RF), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), and Gradient Boosting Decision Tree (GBDT), for rice dry biomass estimation and mapping. Taking a major rice cultivation area in southeast China as case study during the 2016 and 2017 growing seasons, a cross-calibrated time series of the Enhanced Vegetation Index (EVI) was obtained from the quad-source optical imagery and on which the aforementioned models were applied, respectively. Results indicate that in the before rice heading scenario, the most accurate dry biomass estimates were obtained by the GBDT model (R2 of 0.82 and RMSE of 191.8 g/m2) followed by the RF model (R2 of 0.79 and RMSE of 197.8 g/m2). After heading, the k-NN model performed best (R2 of 0.43 and RMSE of 452.1 g/m2) followed by the RF model (R2 of 0.42 and RMSE of 464.7 g/m2). Whist the k-NN model performed least in the before heading scenario, SVM performed least in the after heading scenario. These findings may suggest that machine learning regression models based on an ensemble of decision trees (RF and GBDT) are more suitable for the estimation of rice dry biomass, at least with optical satellite imagery. Studies that would extend the evaluation of these machine learning models, to other parameters like leaf area index, and to microwave imagery, are hereby recommended.http://dx.doi.org/10.1080/15481603.2020.1799546paddy ricedry biomassoptical satellitequad-source imagerymachine learning |
| spellingShingle | Lamin R. Mansaray Adam Sheka Kanu Lingbo Yang Jingfeng Huang Fumin Wang Evaluation of machine learning models for rice dry biomass estimation and mapping using quad-source optical imagery GIScience & Remote Sensing paddy rice dry biomass optical satellite quad-source imagery machine learning |
| title | Evaluation of machine learning models for rice dry biomass estimation and mapping using quad-source optical imagery |
| title_full | Evaluation of machine learning models for rice dry biomass estimation and mapping using quad-source optical imagery |
| title_fullStr | Evaluation of machine learning models for rice dry biomass estimation and mapping using quad-source optical imagery |
| title_full_unstemmed | Evaluation of machine learning models for rice dry biomass estimation and mapping using quad-source optical imagery |
| title_short | Evaluation of machine learning models for rice dry biomass estimation and mapping using quad-source optical imagery |
| title_sort | evaluation of machine learning models for rice dry biomass estimation and mapping using quad source optical imagery |
| topic | paddy rice dry biomass optical satellite quad-source imagery machine learning |
| url | http://dx.doi.org/10.1080/15481603.2020.1799546 |
| work_keys_str_mv | AT laminrmansaray evaluationofmachinelearningmodelsforricedrybiomassestimationandmappingusingquadsourceopticalimagery AT adamshekakanu evaluationofmachinelearningmodelsforricedrybiomassestimationandmappingusingquadsourceopticalimagery AT lingboyang evaluationofmachinelearningmodelsforricedrybiomassestimationandmappingusingquadsourceopticalimagery AT jingfenghuang evaluationofmachinelearningmodelsforricedrybiomassestimationandmappingusingquadsourceopticalimagery AT fuminwang evaluationofmachinelearningmodelsforricedrybiomassestimationandmappingusingquadsourceopticalimagery |