AI SearchModeling rice pest occurrence in Thailand using a combination of satellite time series and machine learning
Call Number: AIT Diss. no.RS-20-05 Material type:
SeriesSeries: Asian Institute of Technology. Dissertation ; no. RS-20-05Publication details: Pathum Thani, Thailand : Asian Institute of Technology, 2020Description: 90 leaves : illSubject(s): Online resources: Dissertation note: Thesis (Ph.D.) - Asian Institute of Technology, 2020 Summary: The brown planthopper Nilaparvata lugens (BPH) is one of the most harmful insect pests in rice paddy fields, which causes considerable yield loss and consequent economic problems, particularly in the central plain of Thailand. Accurate and timely forecasting of pest population incidence would support farmers in planning effective mitigation. In this study, artificial neural network (ANN), random forest (RF) and classic multiple linear regression (MLR) analyses were applied and compared to forecast the BPH population using ground-based weather and satellite-based host-plant phenology factors during the crop dry season from 2006 to 2016 in the central plain of Thailand. Tmin without lag and NDVI at a one-month lag were selected as the major factors in the multiple linear regression model based on their high correlation coefficients. Moreover, the combination of these variables yielded higher accuracy in predicting light trap catches than weather variables alone. On the testing dataset, ANN model (with R2 and RMSE value of 0.770 and 1.686) performed more accurate than RF model (with R2 and RMSE value of 0.754 and l.737) and MLR model (with R2 and RMSE value of 0.645 and 2.015) for short-term BPH density forecasting. Then, an ANN-based prediction map of BPH abundances in dry season 201112012 from December to March was generated. This finding indicates that the utilization of ground meteorological observations, satellite-derived NDVI time series, and machine learning approaches have the potential to predict BPR population density in support of integrated pest management programs. We expect the results from this study can be applied in conjunction with the satellite- based rice monitoring system developed by the Geo-Informatic and Space Technology Development Agency of Thailand (GISTDA) to support an effective pest early warning system.
| Cover image | Item type | Current library | Home library | Collection | Shelving location | Call number | Materials specified | Vol info | URL | Copy number | Status | Notes | Date due | Barcode | Item holds | Item hold queue priority | Course reserves | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
40-Archives
|
Asian Institute of Technology Library Archives | AIT Diss. no.RS-20-05 (Browse shelf(Opens below)) | 1 | Available | 30050120888499 | |||||||||||||
20-AIT Publication
|
Asian Institute of Technology Library AIT Publications | AIT Diss. no.RS-20-05 (Browse shelf(Opens below)) | 1 | Available | 30050211021810 | |||||||||||||
|
20-AIT Publication
|
Asian Institute of Technology Library AIT Publications | AIT Diss. no.RS-20-05 (Browse shelf(Opens below)) | 2 | Available | 30050211021802 | |||||||||||||
67-Electronic Resource
|
Asian Institute of Technology Library Archives | AIT Diss. no.RS-20-05 (Browse shelf(Opens below)) | Not for loan |
A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Remote Sensing and Geographic Information Systems
Thesis (Ph.D.) - Asian Institute of Technology, 2020
The brown planthopper Nilaparvata lugens (BPH) is one of the most harmful insect pests in rice paddy fields, which causes considerable yield loss and consequent economic problems, particularly in the central plain of Thailand. Accurate and timely forecasting of pest population incidence would support farmers in planning effective mitigation. In this study, artificial neural network (ANN), random forest (RF) and classic multiple linear regression (MLR) analyses were applied and compared to forecast the BPH population using ground-based weather and satellite-based host-plant phenology factors during the crop dry season from 2006 to 2016 in the central plain of Thailand. Tmin without lag and NDVI at a one-month lag were selected as the major factors in the multiple linear regression model based on their high correlation coefficients. Moreover, the combination of these variables yielded higher accuracy in predicting light trap catches than weather variables alone. On the testing dataset, ANN model (with R2 and RMSE value of 0.770 and 1.686) performed more accurate than RF model (with R2 and RMSE value of 0.754 and l.737) and MLR model (with R2 and RMSE value of 0.645 and 2.015) for short-term BPH density forecasting. Then, an ANN-based prediction map of BPH abundances in dry season 201112012 from December to March was generated. This finding indicates that the utilization of ground meteorological observations, satellite-derived NDVI time series, and machine learning approaches have the potential to predict BPR population density in support of integrated pest management programs. We expect the results from this study can be applied in conjunction with the satellite- based rice monitoring system developed by the Geo-Informatic and Space Technology Development Agency of Thailand (GISTDA) to support an effective pest early warning system.
There are no comments on this title.