Due to technical and budget limitations, there are inevitably some trade-offs in the design of remote sensing instruments, making it difficult to acquire high spatiotemporal resolution remote sensing images simultaneously. To address this problem, this paper proposes a new data fusion model named the deep convolutional spatiotemporal fusion network (DCSTFN), which makes full use of a convolutional neural network (CNN) to derive high spatiotemporal resolution images from remotely sensed images with high temporal but low spatial resolution (HTLS) and low temporal but high spatial resolution (LTHS). The DCSTFN model is composed of three major parts: the expansion of the HTLS images, the extraction of high frequency components from LTHS images, and the fusion of extracted features. The inputs of the proposed network include a pair of HTLS and LTHS reference images from a single day and another HTLS image on the prediction date. Convolution is used to extract key features from inputs, and deconvolution is employed to expand the size of HTLS images. The features extracted from HTLS and LTHS images are then fused with the aid of an equation that accounts for temporal ground coverage changes. The output image on the prediction day has the spatial resolution of LTHS and temporal resolution of HTLS. Overall, the DCSTFN model establishes a complex but direct non-linear mapping between the inputs and the output. Experiments with MODerate Resolution Imaging Spectroradiometer (MODIS) and Landsat Operational Land Imager (OLI) images show that the proposed CNN-based approach not only achieves state-of-the-art accuracy, but is also more robust than conventional spatiotemporal fusion algorithms. In addition, DCSTFN is a faster and less time-consuming method to perform the data fusion with the trained network, and can potentially be applied to the bulk processing of archived data.

Intensive land surface change and human activities induced by rapid urbanization are the major causes of the urban heat island (UHI) phenomenon. In this article, we examined the spatial variability of UHI and its relationships with land use and socioeconomic patterns in the Baltimore–DC metropolitan area. Census data, road network as well the digital elevation model (DEM) and average water surface percentage were selected to analyse the correlation between spatial patterns of UHI and socioeconomic factors. The impervious surface (coefficient of determination R² = 0.89) and normalized difference vegetation index (R² = 0.81) were the two most important landscape factors, and population density (R² = 0.57) was the most influential socioeconomic variable in contributing to the UHI intensity. Generally, the socioeconomic variables had smaller influence on the UHI intensity than the landscape variables. Based on the patch analysis, most of the socioeconomic variables influenced the UHI intensity indirectly through changing the physical environment (e.g. impervious surface or forest cover). The selected landscape and socioeconomic variables, except impervious surface percentage, demonstrated third-order polynomial correlation with the UHI intensity. The higher correlations were found within certain ranges such as forest percentage from 0% to 30% and population density from 0 to 5000 km^–2. This research provides a case study to understand the urban land surface, vegetation, and microclimate for urban management and planning.

The remote-sensing based Flood Crop Loss Assessment Service System (RF-CLASS) is a web service based system developed and managed by the Center for Spatial Information Science and Systems (CSISS). The system uses Moderate Resolution Imaging Spectroradiometer (MODIS)-based flood data, which was implemented by the Dartmouth Flood Observatory (DFO), to provide an estimation of crop loss from floods. However, due to the spectral similarity between water and shadow, a noticeable amount of false classification of shadow can be found in the DFO flood products. Traditional methods can be utilized to remove cloud shadow and part of mountain shadow. This paper aims to develop an algorithm to filter out noise from permanent mountain shadow in the flood layer. The result indicates that mountain shadow was significantly removed by using the proposed approach. In addition, the gold standard test indicated a small number of actual water surfaces were misidentified by the proposed algorithm. Furthermore, experiments also suggest that increasing the spatial resolution of the slope helped reduce more noise in mountains. The proposed algorithm achieved acceptable overall accuracy (>80%) in all different filters and higher overall accuracies were observed when using lower slope filters. This research is one of the very first discussions on identifying false flood classification from terrain shadow by using the highly efficient method.

Research in different agricultural sectors, including in crop loss estimation during flood and yield estimation, substantially rely on inundation information. Spaceborne remote sensing has widely been used in the mapping and monitoring of floods. However, the inability of optical remote sensing to cloud penetration and the scarcity of fine temporal resolution SAR data hinder the application of flood mapping in many cases. Soil Moisture Active Passive (SMAP) level 4 products, which are model-driven soil moisture data derived from SMAP observations and are available at 3-h intervals, can offer an intermediate but effective solution. This study maps flood progress in croplands by incorporating SMAP surface soil moisture, soil physical properties, and national floodplain information. Soil moisture above the effective soil porosity is a direct indication of soil saturation. Soil moisture also increases considerably during a flood event. Therefore, this approach took into account three conditions to map the flooded pixels: a minimum of 0.05 m³m⁻³ increment in soil moisture from pre-flood to post-flood condition, soil moisture above the effective soil porosity, and the holding of saturation condition for the 72 consecutive hours. Results indicated that the SMAP-derived maps were able to successfully map most of the flooded areas in the reference maps in the majority of the cases, though with some degree of overestimation (due to the coarse spatial resolution of SMAP). Finally, the inundated croplands are extracted from saturated areas by Spatial Hazard Zone areas (SHFA) of Federal Emergency Management Agency (FEMA) and cropland data layer (CDL). The flood maps extracted from SMAP data are validated with FEMA-declared affected counties as well as with flood maps from other sources.

This study integrated multi-temporal Landsat images, the Markov-Cellular Automation (CA) model, and socioeconomic factors to analyze the historical and future farmland loss in the Delhi metropolitan area, one of the most rapidly urbanized areas in the world. Accordingly, the major objectives of this study were: (1) to classify the land use and land cover (LULC) map using multi-temporal Landsat images from 1994 to 2014; (2) to develop and calibrate the Markov-CA model based on the Markov transition probabilities of LULC classes, the CA diffusion factor, and other ancillary factors; and (3) to analyze and compare the past loss of farmland and predict the future loss of farmland in relation to rapid urban expansion from the year 1995 to 2030. The predicted results indicated the high accuracy of the Markov-CA model, with an overall accuracy of 0.75 and Kappa value of 0.59. The predicted results showed that urban expansion is likely to continue to the year of 2030, though the rate of increase will slow down from the year 2020. The area of farmland has decreased and will continue to decrease at a relatively stable rate. The Markov-CA model provided a better understanding of the past, current, and future trends of LULC change, with farmland loss being a typical change in this region. The predicted result will help planners to develop suitable government policies to guide sustainable urban development in Delhi, India.

Inland aquaculture in Bangladesh has been growing fast in the last decade. The underlying land use/land cover (LULC) change is an important indicator of socioeconomic and food structure change in Bangladesh, and fishpond mapping is essential to understand such LULC change. Previous research often used water indexes (WI), such as Normalized Difference Water Index (NDWI) and Modified Normalized Difference Water Index (MNDWI), to enhance water bodies and use shape-based metrics to assist classification of individual water features, such as coastal aquaculture ponds. However, inland fishponds in Bangladesh are generally extremely small, and little research has investigated mapping of such small water objects without high-resolution images. Thus, this research aimed to bridge the knowledge gap by developing and evaluating an automatic fishpond mapping workflow with Sentinel-2 images that is implemented on Google Earth Engine (GEE) platform. The workflow mainly includes two steps: (1) the spectral filtering phase that uses a pixel selection technique and an image segmentation method to automatically identify all-year-inundated water bodies and (2) spatial filtering phase to further classify all-year-inundated water bodies into fishponds and non-fishponds using object-based features (OBF). To evaluate the performance of the workflow, we conducted a case study in the Singra Upazila of Bangladesh, and our method can efficiently map inland fishponds with a precision score of 0.788. Our results also show that the pixel selection technique is essential in identifying inland fishponds that are generally small. As the workflow is implemented on GEE, it can be conveniently applied to other regions.