Estimation of flood-damaged cropland area using a convolutional neural network
Flood damage to croplands poses a significant threat to global food security. Effective disaster management to cope with future climate change, especially extreme precipitation, requires a robust framework to estimate such damage. For this study, we develop a model based on a convolutional neural ne...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2021-01-01
|
| Series: | Environmental Research Letters |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/1748-9326/abeba0 |
| _version_ | 1797747757302153216 |
|---|---|
| author | Rehenuma Lazin Xinyi Shen Emmanouil Anagnostou |
| author_facet | Rehenuma Lazin Xinyi Shen Emmanouil Anagnostou |
| author_sort | Rehenuma Lazin |
| collection | DOAJ |
| description | Flood damage to croplands poses a significant threat to global food security. Effective disaster management to cope with future climate change, especially extreme precipitation, requires a robust framework to estimate such damage. For this study, we develop a model based on a convolutional neural network to estimate the area (in acres) of cropland damaged by flooding at the county level. Then we demonstrate the model’s performance for the period 2008–2019 over corn and soybean fields in the midwestern United States, which suffer frequent damage from recurrent flooding. We fed the network with remote sensing images and weather fields and divide the growing season into two windows, the early season (May–June) and the late season (July–November) for better performance. The results show mean relative error within $ \pm $ 25% and relative root mean square error within 35%–75% in majority of the counties for most years. Finally, we show that the model forced with meteorological variables alone can provide acceptable accuracy, which indicates it can be applied to forecasting crop damage area in the upcoming season or the studying of future climate impact on crop productivity. In principle, the model can also be applied to food security assessment at the global scale using available records. |
| first_indexed | 2024-03-12T15:56:10Z |
| format | Article |
| id | doaj.art-de64c885511b4b3f973ce4ad9d58e4a4 |
| institution | Directory Open Access Journal |
| issn | 1748-9326 |
| language | English |
| last_indexed | 2024-03-12T15:56:10Z |
| publishDate | 2021-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Environmental Research Letters |
| spelling | doaj.art-de64c885511b4b3f973ce4ad9d58e4a42023-08-09T14:57:06ZengIOP PublishingEnvironmental Research Letters1748-93262021-01-0116505401110.1088/1748-9326/abeba0Estimation of flood-damaged cropland area using a convolutional neural networkRehenuma Lazin0Xinyi Shen1https://orcid.org/0000-0002-7411-003XEmmanouil Anagnostou2Department of Civil and Environmental Engineering, University of Connecticut Storrs , 159 Discovery Drive (IPB-212), Storrs, CT 06269, United States of AmericaDepartment of Civil and Environmental Engineering, University of Connecticut Storrs , 159 Discovery Drive (IPB-212), Storrs, CT 06269, United States of AmericaDepartment of Civil and Environmental Engineering, University of Connecticut Storrs , 159 Discovery Drive (IPB-212), Storrs, CT 06269, United States of AmericaFlood damage to croplands poses a significant threat to global food security. Effective disaster management to cope with future climate change, especially extreme precipitation, requires a robust framework to estimate such damage. For this study, we develop a model based on a convolutional neural network to estimate the area (in acres) of cropland damaged by flooding at the county level. Then we demonstrate the model’s performance for the period 2008–2019 over corn and soybean fields in the midwestern United States, which suffer frequent damage from recurrent flooding. We fed the network with remote sensing images and weather fields and divide the growing season into two windows, the early season (May–June) and the late season (July–November) for better performance. The results show mean relative error within $ \pm $ 25% and relative root mean square error within 35%–75% in majority of the counties for most years. Finally, we show that the model forced with meteorological variables alone can provide acceptable accuracy, which indicates it can be applied to forecasting crop damage area in the upcoming season or the studying of future climate impact on crop productivity. In principle, the model can also be applied to food security assessment at the global scale using available records.https://doi.org/10.1088/1748-9326/abeba0floodremote sensingcrop damagecornsoybeanCNN |
| spellingShingle | Rehenuma Lazin Xinyi Shen Emmanouil Anagnostou Estimation of flood-damaged cropland area using a convolutional neural network Environmental Research Letters flood remote sensing crop damage corn soybean CNN |
| title | Estimation of flood-damaged cropland area using a convolutional neural network |
| title_full | Estimation of flood-damaged cropland area using a convolutional neural network |
| title_fullStr | Estimation of flood-damaged cropland area using a convolutional neural network |
| title_full_unstemmed | Estimation of flood-damaged cropland area using a convolutional neural network |
| title_short | Estimation of flood-damaged cropland area using a convolutional neural network |
| title_sort | estimation of flood damaged cropland area using a convolutional neural network |
| topic | flood remote sensing crop damage corn soybean CNN |
| url | https://doi.org/10.1088/1748-9326/abeba0 |
| work_keys_str_mv | AT rehenumalazin estimationofflooddamagedcroplandareausingaconvolutionalneuralnetwork AT xinyishen estimationofflooddamagedcroplandareausingaconvolutionalneuralnetwork AT emmanouilanagnostou estimationofflooddamagedcroplandareausingaconvolutionalneuralnetwork |