Xinyi Shen

In this study, we developed a climate-informed convolutional neural network (CNN) model to estimate flood damages (in acres) in cropland areas (corn and soybean) across the midwestern USA. We first trained and evaluated the CNN model using gridMET datasets from 2008 to 2020, which serve as the reference dataset for downscaling the Coupled Model Intercomparison Project 5 (CMIP5) projections. We then applied the downscaled climate variables in the CNN model to estimate crop damages for the historical baseline period (1976–2005) and the future mid-century period (2041–2070). Results indicate a wide range of damages, spanning from a − 40% to a + 120% by mid-century in the Midwestern counties of the United States. Most climate models project higher damages in Iowa during the early season and lower damages in Minnesota counties during late-season flooding. Due to the varying trends of the environmental variables in the climate models, our model shows discrepancies in projected crop damages. Despite these uncertainties, the findings of this study provide valuable insights into potential future patterns of flood-related crop damages.

In the past few decades, drastic human activities such as urban expansion, agricultural and pastoral activities, water conservancy construction, deforestation, mining, and tourism have significantly altered regional ecological environments

Saudi Arabia is threatened by recurrent flash floods caused by extreme precipitation events. To mitigate the risks associated with these natural disasters, we implemented an advanced nationwide flash flood forecast system, boosting disaster preparedness and response. A noteworthy feature of this system is its national-scale operational approach, providing comprehensive coverage across the entire country. Using cutting-edge technology, the setup incorporates a state-of-the-art, three-component system that couples an atmospheric model with hydrological and hydrodynamic models to enable the prediction of precipitation patterns and their potential impacts on local communities. This paper showcases the system’s effectiveness during an extreme precipitation event that struck Jeddah on 24 November 2022. The event, recorded as the heaviest rainfall in the region’s history, led to widespread flash floods, highlighting the critical need for accurate and timely forecasting. The flash flood forecast system proved to be an effective tool, enabling authorities to issue warnings well before the flooding, allowing residents to take precautionary measures, and allowing emergency responders to mobilize resources effectively.

On June 6, 2023, the Kakhovka Dam in Ukraine experienced a catastrophic breach that led to the loss of life and substantial economic values. Prior to the breach, the supporting structures downstream of the spillway had shown signs of being compromised. Here, we use multi-source satellite data, meteorological reanalysis, and dam design criteria to document the dam’s pre-failure condition. We find that anomalous operation of the Kakhovka Dam began in November 2022, following the destruction of a bridge segment, which led to persistent overtopping from late April 2023 up to the breach, contributing to the erosion of the spillway foundation. Moreover, our findings also highlight safety and risk-reduction measures pivotal in avoiding such scenarios. To help prevent future disasters, we advocate for greater transparency in the design parameters of key water structures to enable risk management, and conclude that remote sensing technology can help ensuring water infrastructure safety.

Ecological droughts in rivers, as a new type of drought, have been greatly discussed in the past decade. Although various studies have been conducted to identify and evaluate ecological droughts in rivers from different indices, a forecast model for this type of drought is still lacking. In this paper, a numerical weather forecast, a hydrological model, and a generalized Bayesian model are employed to establish a new general framework for the probabilistic forecasting of ecological droughts in rivers, and the Daitou section in China is selected as the study area to examine the performance of the new framework. The results show that the hydrological model can accurately simulate the monthly streamflow with a Nash–Sutcliffe efficiency of 0.91 in the validation period, which means that the model can be used to reconstruct the natural streamflow from the impact of an upstream reservoir. Based on a comparison of ecological drought events from the observed and model-simulated streamflow series, the events from the observed series have a larger deficit volume and a longer duration of ecological droughts after 2014, indicating that human activities may lead to a more severe situation of ecological droughts. Furthermore, due to the uncertainty of precipitation forecasts, a probabilistic precipitation forecast is employed for probabilistic ecological drought forecasting. Compared to the deterministic forecast, the probabilistic ecological drought forecast has better performance, with a Brier score decrease of 0.35 to 0.18 and can provide more information about the risk of ecological droughts. In general, the new probabilistic framework developed in this study can serve as a basis for the development of early-warning systems and countermeasures for ecological droughts.

With the rapid development of meteorological models, numerical weather prediction is increasingly used in flood forecasting and reservoir regulation, but its forecasting ability is limited by the large amount of uncertainty from meteorological systems. In this paper, a new, hybrid framework is developed to improve numerical precipitation forecasting by combining the multimodel ensemble and probabilistic postprocessing methods. The results show that the multimodel ensemble method used in this paper is an efficient way to reduce prediction errors, especially missing alarm errors. In a comparison of the probabilistic postprocessors based the generalized Bayesian model (GBM) and bivariate probabilistic model (BPM), the GBM shows better performance from the aspects of indicators and is more suitable for real-time applications. Meanwhile, the assessment of probabilistic results shows that the skill of probabilistic precipitation forecasts is related to the quality of their inputs. According to these results, a new hybrid framework is proposed by taking the results from multimodel ensemble as the input of probabilistic postprocessor. Compared to using the raw numerical in GBM, the hybrid framework improves the accuracy, sharpness, reliability, and resolution ability from different lead times by 2–13%, 1–22%, and 0–12% respectively, especially when the lead time is less than 4 d, the improvement can reach 9–13%, 10–22%, and 5–12% respectively. In conclusion, the hybrid two-step framework can provide a more skillful precipitation forecast, which can be useful for flood forecasting and reservoir regulation.

In this communication, we present the exposure of agricultural lands to the flooding caused by extreme precipitation in western Europe from 12 to 15 July 2021. Overlaying the flood inundation maps derived from the near-real-time RAdar-Produced Inundation Diary (RAPID) system on the Coordination of information on the environment (CORINE) Land Cover map we estimate a 1920 km² area affected by the flooding, with 64 % representing agricultural land. Among the inundated agricultural land, 36 % of the area is pastures while 34 % is arable land. Most agricultural flood exposure is found in eastern France along the Rhône River, the southern Netherlands along the Meuse River, and western Germany along the Rhine River.

Each year throughout the contiguous United States (CONUS), flood hazards cause damage amounting to billions of dollars in homeowner insurance claims. As climate change threatens to raise the frequency and severity of flooding in vulnerable areas, the ability to predict the number of property insurance claims resulting from flood events becomes increasingly important to flood resilience. Based on random forest, we develop a flood property Insurance Claims model (iClaim) by fusing records from the National Flood Insurance Program (NFIP), including building locations, topography, basin morphometry, and land cover, with data from multiple sources of hydrometeorological variables, including flood extent, precipitation, and operational river-stage and oceanic water-level measurements. The model utilizes two steps—damage level classification and claim number regression—and subsampling strategies designed accordingly to reduce overfitting and underfitting caused by the flood claim samples, which are unevenly distributed and widely ranged. We evaluate the model using 446,446 grid samples identified from 589 flood events occurring from 2016 to 2019 over CONUS, overlapping 258,159 claims out of a total of 287,439 NFIP records of the same period. Our rigorous validation yields acceptable performance at the grid/event, county/event, and event accumulative level, with R² over 0.5, 0.9, and 0.95, respectively. We conclude that the iClaim model can be used in many application scenarios, including assessing flood impact and improving flood resilience.

Most existing inundation inventories are based on surveys, news, or passive remote sensing imagery. Affected by spatiotemporal resolution or weather conditions, these inventories are limited in spatial details or coverage. Satellite synthetic aperture radar (SAR) data have recently enabled flood mapping at unprecedented spatiotemporal resolution. However, the bottleneck in producing SAR-based flood maps is the requirement of expert manual processing to maintain acceptable accuracy by most SAR-driven mapping techniques. To fill the vacancy, we generate a high-resolution (10 m) flood inundation dataset over the contiguous United States (CONUS) from nearly the entire Sentinel-1 SAR archive (from January 2016 to the present), using a recently developed automated Radar Produced Inundation Diary (RAPID) system. RAPID uses U.S. Geological Survey (USGS) water watch system and accumulated precipitation to identify SAR images that potentially overlap a flood event. The dataset include inundation events with the temporal scale from several days to months. Concluded from all 559 overlapping images in the period from 2016 to the first half of 2019, the comparison of the proposed dataset against the USGS Dynamic Surface Water Extent (DSWE) product yields an overall, user, producer agreements, and critical success index of 99.06%, 87.63%, 91.76%, and 81.23%, respectively, demonstrating the high accuracy of the proposed dataset and the robustness of the automated system. We anticipate this archive to facilitate many applications, including large-scale flood loss and risk assessment, and inundation model calibration and validation.

Flood damage to croplands poses a significant threat to global food security. Effective disaster management to cope with future climate change, especially extreme precipitation, requires a robust framework to estimate such damage. For this study, we develop a model based on a convolutional neural network to estimate the area (in acres) of cropland damaged by flooding at the county level. Then we demonstrate the model’s performance for the period 2008–2019 over corn and soybean fields in the midwestern United States, which suffer frequent damage from recurrent flooding. We fed the network with remote sensing images and weather fields and divide the growing season into two windows, the early season (May–June) and the late season (July–November) for better performance. The results show mean relative error within ± 25% and relative root mean square error within 35%–75% in majority of the counties for most years. Finally, we show that the model forced with meteorological variables alone can provide acceptable accuracy, which indicates it can be applied to forecasting crop damage area in the upcoming season or the studying of future climate impact on crop productivity. In principle, the model can also be applied to food security assessment at the global scale using available records.