Artificial intelligence and remote sensing for flood and drought detection at the parcel level in paddy fields

Floods and droughts cause catastrophic damage in paddy fields and create unprecedented issues for farmers and the country's economy. The victims need to be compensated for their loss based on the validation of the farmers' claims. Mobile applications have allowed farmers to claim losses by providing mobile photos and polygons of their land plots drawn on satellite base maps. With the use of remote sensing and artificial intelligence, it is possible to automate the process of detecting flood and drought disasters at a parcel level without manual inspection in each disaster-claimed field, saving money and time.The first approach is to study two deep learning-based methods that can verify these claims from the geo-tagged photographs sent by the farmers of their farms at the time of the disaster. Moreover, we demonstrate and compare the efficiency of the two methods: pixel-based semantic segmentation using DeepLabv3+ and an object-based scene recognition method using PlacesCNN. Both of the methods are powered by ResNet architecture backbones. Due to the unavailability of existing datasets for agricultural scenes, especially for the paddy farms, we prepare our own training dataset to train the Deeplabv3+ model and use an existing dataset for the PlacesCNN model. We further create a decision-based method framework that allows us to predict flood and drought from several other classes. The DeepLabv3+ and PlacesCNN-based methods achieve an accuracy of 89.09\% and 93.64\%, respectively. Our experiments show that the object-based method is superior to the pixel-based approach in terms of accuracy, data preparation, computational speed, and expense.The second approach is to use polygons provided by the farmers to access satellite images, one optical and another SAR. We study diverse methods to verify those claims at a parcel level by employing (i) Normalized Difference Vegetation Index (NDVI) and (ii) Normalized Difference Water Index (NDWI) on Sentinel-2A images, (iii) Classification and Regression Tree (CART) on Sentinel-1 SAR GRD images, and (iv) PlacesCNN on mobile photos in case the optical satellite images are disturbed by cloud coverage. To address the disturbance from clouds, we study the combination of multi-modal methods---NDVI+PlacesCNN and NDWI+PlacesCNN---that allow 86.21\% and 83.79\% accuracy in flood detection and 73.40\% and 81.91\% in drought detection, respectively. The SAR-based method outperforms the other methods in terms of accuracy in flood (98.77\%) and drought (99.44\%) detection, data acquisition, parcel coverage, cloud disturbance, and observing the area proportion of disasters in the field. The experiments conclude that the method of CART on SAR images is the most reliable to verify farmers' claims for compensation. In addition, the CNN-based method's performance on mobile photos is adequate, providing an alternative for the CART method in the case of data unavailability while using SAR images.