The deficiency of fine-resolution satellite-derived land surface temperature (LST) has impeded the meticulous exploration of the urban thermal environment at micro spatial scales. Although the LST downscaling methods are well-documented, the scale dependence between LST and environmental factors has been rarely considered in the regression establishment. This article proposes a new method (MGWRK) coupling multiscale geographically weighted regression (MGWR) and area-to-point kriging (ATPK) to generate fine-resolution LST maps over heterogeneous landscapes. Technically, normalized difference vegetation index (NDVI), normalized difference built-up index (NDBI), and albedo are selected using random forests (RF) as scale factors. First, the spatial and temporal robustness of MGWRK is evaluated by downscaling aggregated Landsat-8 Thermal Infrared Sensor images (1000-m) into finer resolutions of 500, 400, 300, 200, and 100-m in different seasons (spring, summer, and winter). Results reveal that MGWRK is superior to GWR and DisTrad methods for spatial details improvement (SSIM > 0.93) and LST fidelity ( ${\bm{R}^2}$ > 0.91) under all scales and in the seasons. Second, MGWRK is utilized to downscale the synchronous 1000-m Moderate Resolution Imaging Spectroradiometer (MODIS) LST map into 100-m. The quantitative and qualitative result substantiates that MGWRK obtains ideal performance when applied on MODIS data with few LST distortion ( ${\bm{R}^2}\; = \;0.915$ , RMSE = 1.607 K) and obvious spatial information enrichment (SSIM = 0.903).

Climate change has caused an increase in the frequency of flood events. Rapid and accurate flood mapping is essential for disaster monitoring and risk assessment. The normalized difference flood index (NDFI) is a change detection method with the characteristics of efficient processing and less manual intervention, which can quickly obtain flood information. However, the NDFI method would misclassify some permanent water bodies in lakes and rivers into floods. We presented a framework by combining NDFI calculated from synthetic aperture radar images and a summer permanent water bodies (SPWB) exclusion layer derived from optical remote sensing surface reflectance data, abbreviated as NDFI-SPWB. This framework was further verified by the flood event in the Yangtze river basin in July 2020. Results show that the NDFI-SPWB framework can increase the user accuracy by approximately 10% and the Kappa coefficient by approximately 0.08 compared with the original NDFI method, which verifies the feasibility and effectiveness of the proposed framework.

Monitoring and assessing urban flood disasters is the key to reducing the damage of this hazard. The urban surveillance video, with the advantages of flexibility and low cost, has been used as an effective real-time data source to monitor urban flooding. The paper presents an inundated area extraction method based on raindrop photometric model. The proposed method operates on the video and divides the task into two steps: (1) extracting water surface, followed by (2) refining inundated areas. At the first step in the process, the water covered areas are extracted from the variation of video in time series. This procedure was an improved version of the raindrop photometric model. Constrained information, especially road ranges, was obtained from video background image which has eliminated interference factors. Then inundated areas can be refined with the constraint information. Experiments performed on different locations show that the proposed method can provide more reliable results than the traditional method based on spectral features.

The spectral index provides a feasible and efficient method for extracting land surface water from satellite images. However, existing methods at the pixel scale consider only water bodies but disregard complicated mixtures. Emerging subpixel–scale methods improve water mapping a detailed description, but they still fail to achieve precise identification of various types of mixed pixels. This deficiency restricts the further development and application of the spectral index method. In this study, we proposed a novel spatial–spectral extraction method that utilizes double thresholds in describing pixels at the subpixel scale. This method combines spatial and spectral attributes to refine and decompose mixed water–land pixels. In this manner, a stepwise approach is adopted to achieve the optimal result instead of the common single–judging method. The experiments use moderate spatial–resolution images, such as those taken by Landsat–8 Operational Land Imager, GF–1’s wide field view multispectral camera and the Sentinel–2A satellite. Results confirm that the proposed method can be applied to common moderate spatial–resolution satellite images. This method achieves better accuracy than existing methods. The insensitivity of threshold selection ensures that the proposed method maintains high precision in actual applications.

kNN-MT presents a new paradigm for domain adaptation by building an external datastore, which usually saves all target language token occurrences in the parallel corpus. As a result, the constructed datastore is usually large and possibly redundant. In this paper, we investigate the interpretability issue of this approach: what knowledge does the NMT model need? We propose the notion of local correctness (LAC) as a new angle, which describes the potential translation correctness for a single entry and for a given neighborhood. Empirical study shows that our investigation successfully finds the conditions where the NMT model could easily fail and need related knowledge. Experiments on six diverse target domains and two language-pairs show that pruning according to local correctness brings a light and more explainable memory for kNN-MT domain adaptation.