Model for Predicting Rice Yield from Reflectance Index and Weather Variables in Lowland Rice Fields
Smallholder rice farmers need a multi-purpose model to forecast yield and manage limited resources such as fertiliser, irrigation water supply in-season, thus optimising inputs and increasing rice yield. Active sensing tools like Canopeo and GreenSeeker-NDVI have provided the opportunity to monitor...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/12/2/130 |
| _version_ | 1827658018666315776 |
|---|---|
| author | Chinaza B. Onwuchekwa-Henry Floris Van Ogtrop Rose Roche Daniel K. Y. Tan |
| author_facet | Chinaza B. Onwuchekwa-Henry Floris Van Ogtrop Rose Roche Daniel K. Y. Tan |
| author_sort | Chinaza B. Onwuchekwa-Henry |
| collection | DOAJ |
| description | Smallholder rice farmers need a multi-purpose model to forecast yield and manage limited resources such as fertiliser, irrigation water supply in-season, thus optimising inputs and increasing rice yield. Active sensing tools like Canopeo and GreenSeeker-NDVI have provided the opportunity to monitor crop health and development at different growth stages. In this study, we assessed the effectiveness of in-season estimation of rice yield in lowland fields of northwest Cambodia using weather data and vegetation cover information measured with; (1) the mobile app-Canopeo, and (2) the conventional GreenSeeker hand-held device that measures the normalised difference vegetative index (NDVI). We collected data from a series of on-farm field experiments in the rice-growing regions in 2018 and 2019. Average temperature and cumulative rainfall were calculated at panicle initiation and pre-heading stages when the crop cover index was measured. A generalised additive model (GAM) was generated using log-transformed data for grain yield, with the combined predictors of canopy cover and weather data during panicle initiation and pre-heading stages. The pre-heading stage was the best stage for grain yield prediction with the Canopeo-derived vegetation index and weather data. Overall, the Canopeo index model explained 65% of the variability in rice yield and Canopeo index, average temperature and cumulative rainfall explained 5, 65 and 56% of the yield variability in rice yield, respectively, at the pre-heading stage. The model (Canopeo index and weather data) evaluation for the training set between the observed and the predicted yield indicated an R<sup>2</sup> value of 0.53 and root mean square error (RMSE) was 0.116 kg ha<sup>−1</sup> at the pre-heading stage. When the model was tested on a validation set, the R<sup>2</sup> value was 0.51 (RMSE = 925.533 kg ha<sup>−1</sup>) between the observed and the predicted yield. The NDVI-weather model explained 62% of the variability in yield, NDVI, average temperature and cumulative rainfall explained 3, 62 and 54%, respectively, of the variability in yield for the training set. The NDVI-weather model evaluation for the training set showed a slightly lower fit with R<sup>2</sup> value of 0.51 (RMSE = 0.119 kg ha<sup>−1</sup>) between the observed and the predicted yield at pre-heading stage. The accuracy performance of the model indicated an R<sup>2</sup> value of 0.46 (RMSE = 979.283 kg ha<sup>−1</sup>) at the same growth stage for validation set. The vegetation-derived information from Canopeo index-weather data increasingly correlated with rice yield than NDVI-weather data. Therefore, the Canopeo index-weather model is a flexible and effective tool for the prediction of rice yield in smallholder fields and can potentially be used to identify and manage fertiliser and water supply to maximise productivity in rice production systems. Data availability from more field experiments are needed to test the model’s accuracy and improve its robustness. |
| first_indexed | 2024-03-09T22:53:59Z |
| format | Article |
| id | doaj.art-3721ba2999334af2aad8cabc13bea236 |
| institution | Directory Open Access Journal |
| issn | 2077-0472 |
| language | English |
| last_indexed | 2024-03-09T22:53:59Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj.art-3721ba2999334af2aad8cabc13bea2362023-11-23T18:15:05ZengMDPI AGAgriculture2077-04722022-01-0112213010.3390/agriculture12020130Model for Predicting Rice Yield from Reflectance Index and Weather Variables in Lowland Rice FieldsChinaza B. Onwuchekwa-Henry0Floris Van Ogtrop1Rose Roche2Daniel K. Y. Tan3Sydney Institute of Agriculture, School of Life and Environmental Sciences, Faculty of Science, The University of Sydney, Sydney, NSW 2006, AustraliaSydney Institute of Agriculture, School of Life and Environmental Sciences, Faculty of Science, The University of Sydney, Sydney, NSW 2006, AustraliaAgriculture and Food/DATA61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Canberra, ACT 2601, AustraliaSydney Institute of Agriculture, School of Life and Environmental Sciences, Faculty of Science, The University of Sydney, Sydney, NSW 2006, AustraliaSmallholder rice farmers need a multi-purpose model to forecast yield and manage limited resources such as fertiliser, irrigation water supply in-season, thus optimising inputs and increasing rice yield. Active sensing tools like Canopeo and GreenSeeker-NDVI have provided the opportunity to monitor crop health and development at different growth stages. In this study, we assessed the effectiveness of in-season estimation of rice yield in lowland fields of northwest Cambodia using weather data and vegetation cover information measured with; (1) the mobile app-Canopeo, and (2) the conventional GreenSeeker hand-held device that measures the normalised difference vegetative index (NDVI). We collected data from a series of on-farm field experiments in the rice-growing regions in 2018 and 2019. Average temperature and cumulative rainfall were calculated at panicle initiation and pre-heading stages when the crop cover index was measured. A generalised additive model (GAM) was generated using log-transformed data for grain yield, with the combined predictors of canopy cover and weather data during panicle initiation and pre-heading stages. The pre-heading stage was the best stage for grain yield prediction with the Canopeo-derived vegetation index and weather data. Overall, the Canopeo index model explained 65% of the variability in rice yield and Canopeo index, average temperature and cumulative rainfall explained 5, 65 and 56% of the yield variability in rice yield, respectively, at the pre-heading stage. The model (Canopeo index and weather data) evaluation for the training set between the observed and the predicted yield indicated an R<sup>2</sup> value of 0.53 and root mean square error (RMSE) was 0.116 kg ha<sup>−1</sup> at the pre-heading stage. When the model was tested on a validation set, the R<sup>2</sup> value was 0.51 (RMSE = 925.533 kg ha<sup>−1</sup>) between the observed and the predicted yield. The NDVI-weather model explained 62% of the variability in yield, NDVI, average temperature and cumulative rainfall explained 3, 62 and 54%, respectively, of the variability in yield for the training set. The NDVI-weather model evaluation for the training set showed a slightly lower fit with R<sup>2</sup> value of 0.51 (RMSE = 0.119 kg ha<sup>−1</sup>) between the observed and the predicted yield at pre-heading stage. The accuracy performance of the model indicated an R<sup>2</sup> value of 0.46 (RMSE = 979.283 kg ha<sup>−1</sup>) at the same growth stage for validation set. The vegetation-derived information from Canopeo index-weather data increasingly correlated with rice yield than NDVI-weather data. Therefore, the Canopeo index-weather model is a flexible and effective tool for the prediction of rice yield in smallholder fields and can potentially be used to identify and manage fertiliser and water supply to maximise productivity in rice production systems. Data availability from more field experiments are needed to test the model’s accuracy and improve its robustness.https://www.mdpi.com/2077-0472/12/2/130riceyield predictiongeneralised additive modelactive remote sensors |
| spellingShingle | Chinaza B. Onwuchekwa-Henry Floris Van Ogtrop Rose Roche Daniel K. Y. Tan Model for Predicting Rice Yield from Reflectance Index and Weather Variables in Lowland Rice Fields Agriculture rice yield prediction generalised additive model active remote sensors |
| title | Model for Predicting Rice Yield from Reflectance Index and Weather Variables in Lowland Rice Fields |
| title_full | Model for Predicting Rice Yield from Reflectance Index and Weather Variables in Lowland Rice Fields |
| title_fullStr | Model for Predicting Rice Yield from Reflectance Index and Weather Variables in Lowland Rice Fields |
| title_full_unstemmed | Model for Predicting Rice Yield from Reflectance Index and Weather Variables in Lowland Rice Fields |
| title_short | Model for Predicting Rice Yield from Reflectance Index and Weather Variables in Lowland Rice Fields |
| title_sort | model for predicting rice yield from reflectance index and weather variables in lowland rice fields |
| topic | rice yield prediction generalised additive model active remote sensors |
| url | https://www.mdpi.com/2077-0472/12/2/130 |
| work_keys_str_mv | AT chinazabonwuchekwahenry modelforpredictingriceyieldfromreflectanceindexandweathervariablesinlowlandricefields AT florisvanogtrop modelforpredictingriceyieldfromreflectanceindexandweathervariablesinlowlandricefields AT roseroche modelforpredictingriceyieldfromreflectanceindexandweathervariablesinlowlandricefields AT danielkytan modelforpredictingriceyieldfromreflectanceindexandweathervariablesinlowlandricefields |