Search for: All records

Accurate identification of inundated areas is crucial for mitigating the impacts of flooding, which causes numerous casualties and significant economic losses. While polarimetric synthetic aperture radar (PolSAR) data have been utilized to detect inundated regions, the information contained within PolSAR features remains severely underutilized. We introduce a novel approach that involves extracting a large number of PolSAR features through various PolSAR decomposition techniques, selecting the most important ones using the decision tree–recursive feature elimination (DT-RFE) method, and ultimately detecting inundation using a convolutional neural network (CNN) model. The hybrid DT-RFE–CNN model was trained and tested over a region in southeastern North Carolina during Hurricane Florence on September 18, 2018, using PolSAR features derived from the Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR). In terms of flood-mapping efficacy, the DT-RFE–CNN model outperformed a CNN model that used only PolSAR data across all metrics in both the training and testing stages. The performance of the trained DT-RFE–CNN model was evaluated by testing it over the same region for four more days (September 19, 20, 22, and 23, 2018); it achieved an average accuracy, precision, recall, F1 score, and intersection-over-union of 0.9304, 0.9089, 0.9584, 0.9324, and 0.8738, respectively, outperforming both the classical Otsu method and the FT-Transformer model using features selected by DT-RFE. Finally, we assessed the model’s generalizability by mapping another significant flood event, caused by Hurricane Harvey in Texas between August and September 2017. Based on the results, the hybrid model can accurately detect flooding, even in regions on which it has not been trained. Thus, the proposed method can facilitate flood monitoring and response efforts. 

Abstract Although many substorm‐related observations have been made, we still have limited insight into propagation of the plasma and field perturbations in Pi2 frequencies (∼7–25 mHz) in association with substorm aurora, particularly from the auroral source region in the inner magnetosphere to the ground. In this study, we present conjugate observations of a substorm brightening aurora using an all‐sky camera and an inner‐magnetospheric satellite Arase atL ∼ 5. A camera at Gakona (62.39°N, 214.78°E), Alaska, observed a substorm auroral brightening on 28 December 2018, and the footprint of the satellite was located just equatorward of the aurora. Around the timing of the auroral brightening, the satellite observed a series of quasi‐periodic variations in the electric and magnetic fields and in the energy flux of electrons and ions. We demonstrate that the diamagnetic variations of thermal pressure and medium‐energy ion energy flux in the inner magnetosphere show approximately one‐to‐one correspondence with the oscillations in luminosity of the substorm brightening aurora and high‐latitudinal Pi2 pulsations on the ground. We also found their anti‐correlation with low‐energy electrons. Cavity‐type Pi2 pulsations were observed at mid‐ and low‐latitudinal stations. Based on these observations, we suggest that a wave phenomenon in the substorm auroral source region, like ballooning type instability, play an important role in the development of substorm and related auroral brightening and high‐latitude Pi2, and that the variation of the auroral luminosity was directly driven by keV electrons which were modulated by Alfven waves in the inner magnetosphere.