Amirhossein Rostami

Flooding is a global problem that impacts people, communities, and governments every year. A better understanding of flooding in an area can enable an improved emergency response before a flood hits. Flood maps are a crucial tool to translate what, for most, is an abstract streamflow into a more understandable and actionable representation of who and what is at risk. Satellite-based flood maps are a useful tool that has potential global applications. We developed methods to determine areas that are suitable for generating satellite-based synthetic flood maps. For our processes, we used Forecasting Inundation Extents using REOF analysis (FIER), a data-driven method of synthesizing flood maps by correlating extracted spatial and temporal patterns from satellite imagery with historical hydrological variables. To overcome the limitation of only using places where gauges are installed, we used large-scale hydrological models, namely the National Water Model (NWM) and the GEOGLOWS Streamflow Model, to provide simulated retrospective streamflow data to train our model. We evaluated locations where both optical and radar imagery would be suitable for creating these models. The procedures we developed and the results that we obtained are potentially transferable to many satellite data sources and methods of model generation.

Floods, one of the costliest, and most frequent hazards, are expected to worsen in the U.S. due to climate change. The real-time forecasting of flood inundations is extremely important for proactive decision-making to reduce damage. However, traditional forecasting methods face challenges in terms of implementation and scalability due to computational burdens and data availability issues. Current forecasting services in the U.S. largely rely on hydrodynamic modeling, limited to river reaches near in situ gauges and requiring extensive data for model setup and calibration. Here, we have successfully adapted the Forecasting Inundation Extents using REOF (FIER) analysis framework to produce forecasted water fraction maps in two U.S. flood-prone regions, specifically the Red River of the North Basin and the Upper Mississippi Alluvial Plain, utilizing Visible Infrared Imaging Radiometer Suite (VIIRS) optical imagery and the National Water Model. Comparing against historical VIIRS imagery for the same dates, FIER 1- to 8-day medium-range pseudo-forecasts show that about 70–80% of pixels exhibit absolute errors of less than 30%. Although originally developed utilizing Synthetic Aperture Radar (SAR) images, this study demonstrated FIER’s versatility and effectiveness in flood forecasting by demonstrating its successful adaptation with optical VIIRS imagery which provides daily water fraction product, offering more historical observations to be used as inputs for FIER during peak flood times, particularly in regions where flooding commonly happens in a short period rather than following a broad seasonal pattern.

Radiative Transfer Models (RTMs) are one of the major building blocks of remote-sensing data analysis that are widely used for various tasks such as atmospheric correction of satellite imagery. Although high-fidelity physical RTMs such as MODTRAN are considered to offer the best possible modeling of atmospheric procedures, they are computationally demanding and require a lot of parameters that should be tuned by an expert. Therefore, there is a need for surrogate models for the physical RTM codes that can mitigate these drawbacks while offering an acceptable performance. This study aimed to suggest surrogate models for the MODTRAN RTM using deep-learning models. For this purpose, the top of atmosphere (TOA) spectra calculated by the MODTRAN code as well as the bottom of atmosphere (BOA) input spectra and other atmospheric parameters such as temperature and water vapor content observations were collected and used as the training dataset. Two deep-learning regression models, including a fully connected network (FCN) and an auto-encoder (AE), as well as a random forest (RF) machine-learning regression model were trained. The results of these models were assessed using the three evaluation metrics root mean squared error (RMSE), regression coefficient (R²), and spectral angle mapper (SAM). The evaluations indicated that the AE offered the best performance in all the metrics, with RMSE, R², and SAM scores of 0.0087, 0.9906, and 1.4295 degrees, respectively, in the best-case scenarios. These results showed that deep-learning models can better reproduce results via high-fidelity physical RTMs.

Active fires are devastating natural disasters that cause socio-economical damage across the globe. The detection and mapping of these disasters require efficient tools, scientific methods, and reliable observations. Satellite images have been widely used for active fire detection (AFD) during the past years due to their nearly global coverage. However, accurate AFD and mapping in satellite imagery is still a challenging task in the remote sensing community, which mainly uses traditional methods. Deep learning (DL) methods have recently yielded outstanding results in remote sensing applications. Nevertheless, less attention has been given to them for AFD in satellite imagery. This study presented a deep convolutional neural network (CNN) “MultiScale-Net” for AFD in Landsat-8 datasets at the pixel level. The proposed network had two main characteristics: (1) several convolution kernels with multiple sizes, and (2) dilated convolution layers (DCLs) with various dilation rates. Moreover, this paper suggested an innovative Active Fire Index (AFI) for AFD. AFI was added to the network inputs consisting of the SWIR2, SWIR1, and Blue bands to improve the performance of the MultiScale-Net. In an ablation analysis, three different scenarios were designed for multi-size kernels, dilation rates, and input variables individually, resulting in 27 distinct models. The quantitative results indicated that the model with AFI-SWIR2-SWIR1-Blue as the input variables, using multiple kernels of sizes 3 × 3, 5 × 5, and 7 × 7 simultaneously, and a dilation rate of 2, achieved the highest F1-score and IoU of 91.62% and 84.54%, respectively. Stacking AFI with the three Landsat-8 bands led to fewer false negative (FN) pixels. Furthermore, our qualitative assessment revealed that these models could detect single fire pixels detached from the large fire zones by taking advantage of multi-size kernels. Overall, the MultiScale-Net met expectations in detecting fires of varying sizes and shapes over challenging test samples.