Development of a spatially complete floodplain map of the conterminous United States using random forest

Climate Change Will Impact Surface Water Extents and Dynamics Across the Central United States

Climate change is projected to impact river, lake, and wetland hydrology, with global implications for the condition and productivity of aquatic ecosystems. We integrated Sentinel-1 and Sentinel-2 based algorithms to track monthly surface water extent (2017-2021) for 32 sites across the central United States (U.S.). Median surface water extent was highly variable across sites, ranging from 3.9% to 45.1% of a site. To account for landscape-based differences (e.g., water storage capacity, land use) in the response of surface water extents to meteorological conditions, individual statistical models were developed for each site. Future changes to climate were defined as the difference between 2006-2025 and 2061-2080 using MACA-CMIP5 (MACAv2-METDATA) Global Circulation Models. Time series of climate change adjusted surface water extents were projected. Annually, 19 of the 32 sites under RCP4.5 and 22 of the 32 sites under RCP8.5 were projected to show an average decline in surface water extent, with drying most consistent across the southeast central, southwest central, and midwest central U.S. Projected declines under surface water dry conditions at these sites suggest greater impacts of drought events are likely in the future. Projected changes were seasonally variable, with the greatest decline in surface water extent expected in summer and fall seasons. In contrast, many north central sites showed a projected increase in surface water in most seasons, relative to the 2017-2021 period, likely attributable to projected increases in winter and spring precipitation exceeding increases in projected temperature.

Quantitative assessment of Land use/land cover changes in a developing region using machine learning algorithms: A case study in the Kurdistan Region, Iraq

The identification of land use/land cover (LULC) changes is important for monitoring, evaluating, and preserving natural resources. In the Kurdistan region, the utilization of remotely sensed data to assess the effectiveness of machine learning algorithms (MLAs) for LULC classification and change detection analysis has been limited. This study monitors and analyzes LULC changes in the study area from 1991 to 2021 using a quantitative approach with multi-temporal Landsat imagery. Five MLAs were applied: Support Vector Machine (SVM), Random Forest (RF), Artificial Neural Network (ANN), K-Nearest Neighbor (KNN), and Extreme Gradient Boosting (XGBoost). The results showed that the RF algorithm produced the most accurate maps of the three-decade study period, accompanied by a high kappa coefficient (0.93-0.97) compared with the SVM (0.91-0.95), ANN (0.91-0.96), KNN (0.92-0.96), and XGBoost (0.92-0.95) algorithms. Consequently, the RF classifier was implemented to categorize all obtainable satellite images. Socioeconomic changes throughout these transition periods were revealed by the change detection results. Rangeland and barren land areas decreased by 11.33 % (-402.03 km2) and 6.68 % (-236.8 km2), respectively. The transmission increases of 13.54 % (480.18 km2), 3.43 % (151.74 km2), and 0.71 % (25.22 km2) occurred in agricultural land, forest, and built-up areas, respectively. The outcomes of this study contribute significantly to LULC monitoring in developing regions, guiding stakeholders to identify vulnerable areas for better land use planning and sustainable environmental protection.

Human alterations of the global floodplains 1992-2019

Floodplains provide critical ecosystem services; however, loss of natural floodplain functions caused by human alterations increase flood risks and lead to massive loss of life and property. Despite recent calls for improved floodplain protection and management, a comprehensive, global-scale assessment quantifying human floodplain alterations does not exist. We developed the first publicly available global dataset that quantifies human alterations in 15 million km2 floodplains along 520 major river basins during the recent 27 years (1992-2019) at 250-m resolution. To maximize the reuse of our dataset and advance the open science of human floodplain alteration, we developed three web-based programming tools supported with tutorials and step-by-step audiovisual instructions. Our data reveal a significant loss of natural floodplains worldwide with 460,000 km2 of new agricultural and 140,000 km2 of new developed areas between 1992 and 2019. This dataset offers critical new insights into how floodplains are being destroyed, which will help decision-makers to reinforce strategies to conserve and restore floodplain functions and habitat.

Mapping global non-floodplain wetlands

Non-floodplain wetlands - those located outside the floodplains - have emerged as integral components to watershed resilience, contributing hydrologic and biogeochemical functions affecting watershed-scale flooding extent, drought magnitude, and water-quality maintenance. However, the absence of a global dataset of non-floodplain wetlands limits their necessary incorporation into water quality and quantity management decisions and affects wetland-focused wildlife habitat conservation outcomes. We addressed this critical need by developing a publicly available "Global NFW" (Non-Floodplain Wetland) dataset, comprised of a global river-floodplain map at 90 m resolution coupled with a global ensemble wetland map incorporating multiple wetland-focused data layers. The floodplain, wetland, and non-floodplain wetland spatial data developed here were successfully validated within 21 large and heterogenous basins across the conterminous United States. We identified nearly 33 million potential non-floodplain wetlands with an estimated global extent of over 16×106 km2. Non-floodplain wetland pixels comprised 53% of globally identified wetland pixels, meaning the majority of the globe's wetlands likely occur external to river floodplains and coastal habitats. The identified global NFWs were typically small (median 0.039 km2), with a global median size ranging from 0.018-0.138 km2. This novel geospatial Global NFW static dataset advances wetland conservation and resource-management goals while providing a foundation for global non-floodplain wetland functional assessments, facilitating non-floodplain wetland inclusion in hydrological, biogeochemical, and biological model development. The data are freely available through the United States Environmental Protection Agency's Environmental Dataset Gateway (https://gaftp.epa.gov/EPADataCommons/ORD/Global_NonFloodplain_Wetlands/, last access: 24 May 2023) and through https://doi.org/10.23719/1528331 (Lane et al., 2023a).

Systemic Financial Risk Arising from Residential Flood Losses

Direct damage from flooding at residential properties has typically been categorized as insured, with liabilities accruing to insurers, or uninsured, with costs accruing to property owners. However, residential flooding can also expose lenders and local governments to financial risk, though the distribution of this risk is not well understood. Flood losses are not limited to direct damages, but also include indirect effects such as decreases in property values, which can be substantial, though are rarely well quantified. The combination of direct damage and property value decrease influences rates of mortgage default and property abandonment in the wake of a flood, creating financial risk. In this research, property-level data on sales, mortgages, and insurance claims are used in combination with machine learning techniques and geostatistical methods to provide estimates of flood losses that are then utilized to evaluate the risk of default and abandonment in eastern North Carolina following Hurricane Florence (2018). Within the study area, Hurricane Florence generated $366M in observed insured damages and an estimated $1.77B in combined uninsured damages and property value decreases. Property owners, lenders, and local governments were exposed to an additional $562M in potential losses due to increased rates of default and abandonment. Areas with lower pre-flood property values were exposed to greater risk than areas with higher valued properties. Results suggest more highly resolved estimates of a flooding event's systemic financial risk may be useful in developing improved flood resilience strategies.

Water quality status response to multiple anthropogenic activities in urban river

Water quality evaluation and degrading factors identification are crucial for predicting water quality evolution trends in an urban river. However, under the coupling of multiple factors, these targets face great challenges. The water quality status response to multiple anthropogenic activities in an urban river was evaluated and predicted based on comprehensive assessment methods and random forest (RF) model. We found that the distribution of each physicochemical parameter exhibits an obvious spatial clustering. The mean pollution level and trophic status of the urban river are medium pollution (water quality index = 59.79; Nemerow's pollution index = 2.00) and light eutrophication (trophic level index = 57.30). The water quality status is sensitive to anthropogenic activities, showing the following order of TLI and NPI values: residential district > industrial district > agricultural district and downtown > suburbs > countryside. According to the redundancy analysis, constructed land (F = 15.90, p < 0.01) and domestic sewage (F = 14.20, p < 0.01) evinced as the crucial factors that aggravated the water quality pollution level. Based on the simulation results of the RF model (variation explained = 94.91%; R² = 0.978), improving domestic sewage treatment standards is the most effective measure to improve the water quality (increased by 40.3-49.3%) in residential and industrial districts. While in a suburban district, improving the domestic sewage collection rate has more effectively (23%) than those in the residential and industrial districts. Conclusively, reducing exogenous pollution input and improving domestic sewage treatment standards are vital to urban river restoration. Clinical trial registration Not applicable.

Fine-Scale Classification of Urban Land Use and Land Cover with PlanetScope Imagery and Machine Learning Strategies in the City of Cape Town, South Africa

Urban land use and land cover (LULC) change can be efficiently monitored with high-resolution satellite products for a variety of purposes, including sustainable planning. These, together with machine learning strategies, have great potential to detect even subtle changes with satisfactory accuracy. In this study, we used PlaneScope Imagery and machine learning strategies (Random Forests, Support Vector Machines, Naïve Bayes and K-Nearest Neighbour) to classify and detect LULC changes over the City of Cape Town between 2016 and 2021. Our results showed that K-Nearest Neighbour outperformed other classifiers by achieving the highest overall classification of accuracy (96.54% with 0.95 kappa), followed by Random Forests (94.8% with 0.92 kappa), Naïve Bayes (93.71% with 0.91 kappa) and Support Vector Machines classifiers with relatively low accuracy values (92.28% with 0.88 kappa). However, the performance of all classifiers was acceptable, exceeding the overall accuracy of more than 90%. Furthermore, the results of change detection from 2016 to 2021 showed that the high-resolution PlanetScope imagery could be used to track changes in LULC over a desired period accurately.

Application of Machine Learning and Process-Based Models for Rainfall-Runoff Simulation in DuPage River Basin, Illinois

Rainfall-runoff simulation is vital for planning and controlling flood control events. Hydrology modeling using Hydrological Engineering Center—Hydrologic Modeling System (HEC-HMS) is accepted globally for event-based or continuous simulation of the rainfall-runoff operation. Similarly, machine learning is a fast-growing discipline that offers numerous alternatives suitable for hydrology research’s high demands and limitations. Conventional and process-based models such as HEC-HMS are typically created at specific spatiotemporal scales and do not easily fit the diversified and complex input parameters. Therefore, in this research, the effectiveness of Random Forest, a machine learning model, was compared with HEC-HMS for the rainfall-runoff process. Furthermore, we also performed a hydraulic simulation in Hydrological Engineering Center—Geospatial River Analysis System (HEC-RAS) using the input discharge obtained from the Random Forest model. The reliability of the Random Forest model and the HEC-HMS model was evaluated using different statistical indexes. The coefficient of determination (R2), standard deviation ratio (RSR), and normalized root mean square error (NRMSE) were 0.94, 0.23, and 0.17 for the training data and 0.72, 0.56, and 0.26 for the testing data, respectively, for the Random Forest model. Similarly, the R2, RSR, and NRMSE were 0.99, 0.16, and 0.06 for the calibration period and 0.96, 0.35, and 0.10 for the validation period, respectively, for the HEC-HMS model. The Random Forest model slightly underestimated peak discharge values, whereas the HEC-HMS model slightly overestimated the peak discharge value. Statistical index values illustrated the good performance of the Random Forest and HEC-HMS models, which revealed the suitability of both models for hydrology analysis. In addition, the flood depth generated by HEC-RAS using the Random Forest predicted discharge underestimated the flood depth during the peak flooding event. This result proves that HEC-HMS could compensate Random Forest for the peak discharge and flood depth during extreme events. In conclusion, the integrated machine learning and physical-based model can provide more confidence in rainfall-runoff and flood depth prediction.

Can a Hierarchical Classification of Sentinel-2 Data Improve Land Cover Mapping?

Monitoring of land cover plays an important role in effective environmental management, assessment of natural resources, environmental protection, urban planning and sustainable development. Increasing demand for accurate and repeatable information on land cover and land cover changes causes rapid development of the advanced, machine learning algorithms dedicated to land cover mapping using satellite images. Free and open access to Sentinel-2 data, characterized with high spatial and temporal resolution, increased the potential to map and to monitor land surface with high accuracy and frequency. Despite a considerable number of approaches towards land cover classification based on satellite data, there is still a challenge to clearly separate complex land cover classes, for example grasslands, arable land and wetlands. The aim of this study is to examine, whether a hierarchal classification of Sentinel-2 data can improve the accuracy of land cover mapping and delineation of complex land cover classes. The study is conducted in the Lodz Province, in central Poland. The pixel-based land cover classification is carried out using the machine learning Random Forest (RF) algorithm, based on a time series of Sentinel-2 imagery acquired in 2020. The following nine land cover classes are mapped: sealed surfaces, woodland broadleaved, woodland coniferous, shrubs, permanent herbaceous (grassy cover), periodically herbaceous (i.e., arable land), mosses, non-vegetated (bare soil) and water bodies. The land cover classification is conducted following two approaches: (1) flat, where all land cover classes are classified together, and (2) hierarchical, where the stratification is applied to first separate the most stable land cover classes and then classifying the most problematic once. The national databases served as the source of the reference sampling plots for the classification process. The process of selection and verification of the reference sampling plots is performed automatically. To assess the stability of the classification models the classification processes are performed iteratively. The results of this study confirmed that the hierarchical approach gave more accurate results compared to the commonly used flat approach. The median of the overall accuracy (OA) of the hierarchical classification was higher by 3–9 percentage points compared to the flat one. Of interest, the OA of the hierarchical classification reached 0.93–0.99, whereas the flat approach reached 0.90. Individual classes are also better classified in the hierarchical approach.

Land use land cover mapping using advanced machine learning classifiers

Due to the recent climate changes such as floods and droughts, there is a need for Land Use Land Cover (LULC) mapping to monitor environmental changes that have effects on ecology, policy management, health and disaster management. As such, in this study, two well-known machine learning classifiers, namely, Support Vector Machine (SVM) and Random Forest (RF), are used for land cover mapping. In addition, two advanced deep learning algorithms, namely, the GAMLP and FSMLP, that are based on the Multi-layer Perceptron (MLP) function are developed in MATLAB programming language. The GAMLP uses a Genetic Algorithm (GA) to optimise parameters of the MLP function and, on the other hand, the FSMLP uses a derivative-free function for optimisation of the MLP function parameters. Three different scenarios using Landsat-8 imagery with spatial resolutions of 30 and 15 m are defined to investigate the effects of data pre-processing on the final predicted LULC map. Results based on the statistical indices, including overall accuracy (OA) and kappa index, show that the developed MLP-based algorithms have relatively high accuracies with higher than 98% correct classification. Besides the statistical indices, final LULC maps are interpreted visually where the GAMLP and FSMLP give the best results for the pre-processed Landsat-8 imagery with a spatial resolution of 15 m, but they have the worst outcomes for the unprocessed Landsat-8 imagery compared to SVM and RF classifiers visually and statistically.

National-scale assessment of decadal river migration at critical bridge infrastructure in the Philippines

River migration represents a geomorphic hazard at sites of critical bridge infrastructure, particularly in rivers where migration rates are high, as in the tropics. In the Philippines, where exposure to flooding and geomorphic risk are considerable, the recent expansion of infrastructural developments warrants quantification of river migration in the vicinity of bridge assets. We analysed publicly available bridge inventory data from the Philippines Department of Public Works and Highways (DPWH) to complete multi-temporal geospatial analysis using three decades worth of Landsat satellite imagery in Google Earth Engine (GEE). For 74 large bridges, we calculated similarity coefficients and quantified changes in width for the active river channel (defined as the wetted channel and unvegetated alluvial deposits) over decadal and engineering (30-year) timescales. Monitoring revealed the diversity of river planform adjustment at bridges in the Philippines (including channel migration, contraction, expansion and avulsion). The mean Jaccard index over decadal (0.65) and engineering (0.50) timescales indicated considerable planform adjustment throughout the national-scale inventory. However, planform adjustment and morphological behaviour varied between bridges. For bridges with substantial planform adjustment, maximum active channel contraction and expansion was equal to 25% of the active channel width over decadal timescales. This magnitude of lateral adjustment is sufficient to imply the need for bridge design to accommodate channel dynamism. For other bridges, the planform remained stable and changes in channel width were limited. Fundamental differences in channel characteristics and morphological behaviours emerged between different valley confinement settings, and between rivers with different channel patterns, indicating the importance of the local geomorphic setting. We recommend satellite remote sensing as a low-cost approach to monitor river planform adjustment with large-scale planimetric changes detectable in Landsat products; these approaches can be applied to other critical infrastructure adjacent to rivers (e.g. road, rail, pipelines) and extended elsewhere to other dynamic riverine settings.

A wavelet-based random forest approach for indoor BTEX spatiotemporal modeling and health risk assessment

This study reports on BTEX concentrations in one of the largest parking garages in Iran with a peak traffic flow reaching up to ~9300 vehicles in the last few days of the Nowruz holidays. Samples were obtained on different days of the week at three main locations in the Zaer Parking Garage. A novel wavelet-based random forest model (WRF) was trained to estimate BTEX concentrations by decomposing temperature, day of the week, sampling location, and relative humidity data with a maximal overlap discrete wavelet transform (MODWT) function and subsequently inputted into the WRF model. The results suggested that the WRF model can reasonably estimate BTEX trends and variations based on high R2 values of 0.96, 0.95, and 0.98 for training, validation, and test data subsets, respectively. The carcinogenic (LTCR) and non-carcinogenic health risk (HI) assessment results indicated a definite carcinogenic risk of benzene (LTCR = 2.22 × 10-4) and high non-carcinogenic risk (HI = 4.51) of BTEX emissions. The results of this study point to the importance of BTEX accumulation in poorly ventilated areas and the utility of machine learning in forecasting air pollution in diverse airsheds such as parking garages.

Geographic Visualization of Mortality in the United States as Related to Healthcare Access by County

This investigation analyzed the impact of place-based inequities on mortality rates in 2014. The team combined mortality data with metrics on health care accessibility, socioeconomic deprivation, and other variables available from publicly available data sets. The investigation team created a centralized database for visualizations that combined mortality data by diagnosis, socioeconomic data, health resource data, and an index of area deprivation. Choropleth maps, scatterplots, and regression analyses were performed to identify the major areas of mortality and how well different measures of the social determinants of health (SDOH) correlate to mortality data. A bivariate color scheme to visually capture both outcomes and SDOH in a choropleth map was shown to be a compact and novel manner to display complex epidemiologic data.

Analysis of 220 Years of Floodplain Population Dynamics in the US at Different Spatial Scales

In this study, we explore the long-term trends of floodplain population dynamics at different spatial scales in the contiguous United States (U.S.). We exploit different types of datasets from 1790–2010—i.e., decadal spatial distribution for the population density in the US, global floodplains dataset, large-scale data of flood occurrence and damage, and structural and nonstructural flood protection measures for the US. At the national level, we found that the population initially settled down within the floodplains and then spread across its territory over time. At the state level, we observed that flood damages and national protection measures might have contributed to a learning effect, which in turn, shaped the floodplain population dynamics over time. Finally, at the county level, other socio-economic factors such as local flood insurances, economic activities, and socio-political context may predominantly influence the dynamics. Our study shows that different influencing factors affect floodplain population dynamics at different spatial scales. These facts are crucial for a reliable development and implementation of flood risk management planning.

A Quantitative Framework for Analyzing Spatial Dynamics of Flood Events: A Case Study of Super Cyclone Amphan

Identifying the flooding risk hotspot is crucial for aiding a rapid response and prioritizes mitigation efforts over large disaster impacted regions. While climate change is increasing the risk of floods in many vulnerable regions of the world, the commonly used crisis map is inefficient and cannot rapidly determine the spatial variation and intensity of flooding extension across the affected areas. In such cases, the Local Indicators of Spatial Association (LISA) statistic can detect heterogeneity or the flooding hotspot at a local spatial scale beyond routine mapping. This area, however, has not yet been studied in the context of the magnitude of the floods. The present study incorporates the LISA methodology including Moran’s I and Getis–Ord Gi* to identify the spatial and temporal heterogeneity of the occurrence of flooding from super cyclone Amphan across 16 coastal districts of Bangladesh. Using the Synthetic Aperture Radar (SAR) data from Sentinel-1 and a Support Vector Machine (SVM) classification, “water” and “land” were classified for the pre-event (16 May 2020) and post-events (22 May, 28 May, and 7 June 2020) of the area under study. A Modified Normalized Difference Water Index (MNDWI), and visual comparison were used to evaluate the flood maps. A compelling agreement was accomplished between the observed and predicted flood maps, with an overall precision of above 95% for all SAR classified images. As per this study, 2233 km2 (8%) of the region is estimated to have been inundated on 22 May. After this point, the intensity and aerial expansion of flood decreased to 1490 km2 by 28 May before it increased slightly to 1520 km2 (2.1% of the study area) on 7 June. The results from LISA indicated that the main flooding hotspots were located in the central part, particularly in the region off the north-east of the mangrove forest. A total of 238 Unions (smallest administrative units) were identified as high flooding hotspots (p < 0.05) on 22 May, but the number of flooding hotspots dropped to 166 in the second week (28 May) after Amphan subsided before it increased to a further 208 hotspots (p < 0.05) on 7 June due to incessant rainfall and riverbank failure in the south-west part of the study area. As such, an appropriate, timely, and cost-effective strategy would be to assess existing flooding management policies through the identified flooding hotspot regions. This identification would then allow for the creation of an improved policy to help curtail the destructive effects of flooding in the future.

Predicting flood insurance claims with hydrologic and socioeconomic demographics via machine learning: Exploring the roles of topography, minority populations, and political dissimilarity

Current research on flooding risk often focuses on understanding hazards, de-emphasizing the complex pathways of exposure and vulnerability. We investigated the use of both hydrologic and social demographic data for flood exposure mapping with Random Forest (RF) regression and classification algorithms trained to predict both parcel- and tract-level flood insurance claims within New York State, US. Topographic characteristics best described flood claim frequency, but RF prediction skill was improved at both spatial scales when socioeconomic data was incorporated. Substantial improvements occurred at the tract-level when the percentage of minority residents, housing stock value and age, and the political dissimilarity index of voting precincts were used to predict insurance claims. Census tracts with higher numbers of claims and greater densities of low-lying tax parcels tended to have low proportions of minority residents, newer houses, and less political similarity to state level government. We compared this data-driven approach and a physically-based pluvial flood routing model for prediction of the spatial extents of flooding claims in two nearby catchments of differing land use. The floodplain we defined with physically based modeling agreed well with existing federal flood insurance rate maps, but underestimated the spatial extents of historical claim generating areas. In contrast, RF classification incorporating hydrologic and socioeconomic demographic data likely overestimated the flood-exposed areas. Our research indicates that quantitative incorporation of social data can improve flooding exposure estimates.

Evaluation of Light Gradient Boosted Machine Learning Technique in Large Scale Land Use and Land Cover Classification

The ability to rapidly produce accurate land use and land cover maps regularly and consistently has been a growing initiative as they have increasingly become an important tool in the efforts to evaluate, monitor, and conserve Earth’s natural resources. Algorithms for supervised classification of satellite images constitute a necessary tool for the building of these maps and they have made it possible to establish remote sensing as the most reliable means of map generation. In this paper, we compare three machine learning techniques: Random Forest, Support Vector Machines, and Light Gradient Boosted Machine, using a 70/30 training/testing evaluation model. Our research evaluates the accuracy of Light Gradient Boosted Machine models against the more classic and trusted Random Forest and Support Vector Machines when it comes to classifying land use and land cover over large geographic areas. We found that the Light Gradient Booted model is marginally more accurate with a 0.01 and 0.059 increase in the overall accuracy compared to Support Vector and Random Forests, respectively, but also performed around 25% quicker on average.

Predictive model for risk of gastric cancer using genetic variants from genome-wide association studies and high-evidence meta-analysis

Genome-wide association studies (GWAS) have identified some single nucleotide polymorphisms (SNPs) associated with the risk of gastric cancer (GCa). However, currently, there is no published predictive model to assess the risk of GCa. In the present study, risk-associated SNPs derived from GWAS and large meta-analyses were selected to construct a predictive model to assess the risk of GCa. A total of 1115 GCa cases and 1172 controls from the eastern Chinese population were included. Logistic regression models were used to identify SNPs that correlated with the risk of GCa. A predictive model to assess the risk of GCa was established by receiver operating characteristic curve analysis. Multifactor dimensionality reduction (MDR) and classification and regression tree (CART) were applied to calculate the effect of high-order gene-environment interactions on risk of the cancer. A total of 42 SNPs were selected for further analysis. The results revealed that ASH1L rs80142782, PKLR rs3762272, PRKAA1 rs13361707, MUC1 rs4072037, PSCA rs2294008, and PLCE1 rs2274223 polymorphisms were associated with a risk of GCa. The area under curve considering both genetic factors and BMI was 3.10% higher than that of BMI alone. MDR analysis revealed that rs13361707 and rs4072307 variants and BMI had interaction effects on susceptibility to GCa, with the highest predictive accuracy (61.23%) and cross-validation consistency (100/100). CART analysis also supported this interaction model that non-overweight status and a six SNP panel could synergistically increase the susceptibility to GCa. The six SNP panel for predicting the risk of GCa may provide new tools for prevention of the cancer based on GWAS and large meta-analyses derived genetic variants.

Social Sensing for Urban Land Use Identification

The utilization of urban land use maps can reveal the patterns of human behavior through the extraction of the socioeconomic and demographic characteristics of urban land use. Remote sensing that holds detailed and abundant information on spectral, textual, contextual, and spatial configurations is crucial to obtaining land use maps that reveal changes in the urban environment. However, social sensing is essential to revealing the socioeconomic and demographic characteristics of urban land use. This data mining approach is related to data cleaning/outlier removal and machine learning, and is used to achieve land use classification from remote and social sensing data. In bicycle and taxi density maps, the daytime destination and nighttime origin density reflects work-related land uses, including commercial and industrial areas. By contrast, the nighttime destination and daytime origin density pattern captures the pattern of residential areas. The accuracy assessment of land use classified maps shows that the integration of remote and social sensing, using the decision tree and random forest methods, yields accuracies of 83% and 86%, respectively. Thus, this approach facilitates an accurate urban land use classification. Urban land use identification can aid policy makers in linking human activities to the socioeconomic consequences of different urban land uses.

Application of Nonhydraulic Delineation Method of Flood Hazard Areas Using LiDAR-Based Data

Fluvial dynamics are an important aspect of land-use planning as well as ecosystem conservation. Lack of floodplain and flood inundation maps can cause severe implication on land-use planning and development as well as in disaster management. However, flood hazard delineation traditionally involves hydrologic models and uses hydraulic data or historical flooding frequency. This entails intensive data gathering, which leads to extensive amount of cost, time, and complex models, while typically only covers a small portion of the landscape. Therefore, alternative approaches had to be explored. This study explores an alternative approach in delineating flood hazard areas through a straightforward interpolation process while using high-resolution LiDAR-based datasets. The objectives of this study are: (1) to delineate flood hazard areas through a straightforward, nonhydraulic, and interpolation procedure using high-resolution (LiDAR-based) datasets and (2) to determine whether using high-resolution data, coupled with a straightforward interpolation procedure, will yield reliable potential flood hazard maps. Results showed that a straightforward interpolation method using LiDAR-based data produces a reliable potential flood zone map. The resulting map can be used as supplementary information for rapid analysis of the topography which could have implications in area development planning and ecological management and best practices.

Repeated Hurricanes Reveal Risks and Opportunities for Social-Ecological Resilience to Flooding and Water Quality Problems

Hurricanes that damage lives and property can also impact pollutant sources and trigger poor water quality. Yet, these water quality impacts that affect both human and natural communities are difficult to quantify. We developed an operational remote sensing-based hurricane flood extent mapping method, examined potential water quality implications of two "500-year" hurricanes in 2016 and 2018, and identified options to increase social-ecological resilience in North Carolina. Flooding detected with synthetic aperture radar (>91% accuracy) extended beyond state-mapped hazard zones. Furthermore, the legal floodplain underestimated impacts for communities with higher proportions of older adults, disabilities, unemployment, and mobile homes, as well as for headwater streams with restricted elevation gradients. Pollution sources were repeatedly affected, including ∼55% of wastewater treatment plant capacity and swine operations that generate ∼500 M tons/y manure. We identified ∼4.8 million km² for possible forest and wetland conservation and ∼1.7 million km² for restoration or altered management opportunities. The results suggest that current hazard mapping is inadequate for resilience planning; increased storm frequency and intensity necessitate modification of design standards, land-use policies, and infrastructure operation. Implementation of interventions can be guided by a greater understanding of social-ecological vulnerabilities within hazard and exposure areas.

A Framework for Modeling Flood Depth Using a Hybrid of Hydraulics and Machine Learning

Solving river engineering problems typically requires river flow characterization, including the prediction of flow depth, flow velocity, and flood extent. Hydraulic models use governing equations of the flow in motion (conservation of mass and momentum principles) to predict the flow characteristics. However, solving such equations can be substantially expensive, depending upon their spatial extension. Moreover, modeling two- or three-dimensional river flows with high-resolution topographic data for large-scale regions (national or continental scale) is next to impossible. Such simulations are required for comprehensive river modeling, where a system of connected rivers is to be simulated simultaneously. Machine Learning (ML) approaches have shown promise for different water resources problems, and they have demonstrated an ability to learn from current data to predict new scenarios, which can enhance the understanding of the systems. The aim of this paper is to present an efficient flood simulation framework that can be applied to large-scale simulations. The framework outlines a novel, quick, efficient and versatile model to identify flooded areas and the flood depth, using a hybrid of hydraulic model and ML measures. To accomplish that, a two-dimensional hydraulic model (iRIC), calibrated by measured water surface elevation data, was used to train two ML models to predict river depth over the domain for an arbitrary discharge. The first ML model included a random forest (RF) classification model, which was used to identify wet or dry nodes over the domain. The second was a multilayer perceptron (MLP) model that was developed and trained by the iRIC simulation results, in order to estimate river depth in wet nodes. For the test data the overall accuracy of 98.5 percent was achieved for the RF classification. The regression coefficient for the MLP model for depth was 0.88. The framework outlined in this paper can be used to couple hydraulics and ML models to reduce the computation time, resources and expenses of large-scale, real-time simulations, specifically for two- or three-dimensional hydraulic modeling, where traditional hydraulic models are infeasible or prohibitively expensive.

Comparative assessment of the flash-flood potential within small mountain catchments using bivariate statistics and their novel hybrid integration with machine learning models

The present study is carried out in the context of the continuous increase, worldwide, of the number of flash-floods phenomena. Also, there is an evident increase of the size of the damages caused by these hazards. Bâsca Chiojdului River Basin is one of the most affected areas in Romania by flash-flood phenomena. Therefore, Flash-Flood Potential Index (FFPI) was defined and calculated across the Bâsca Chiojdului river basin by using one bivariate statistical method (Statistical Index) and its novel ensemble with the following machine learning models: Logistic Regression, Classification and Regression Trees, Multilayer Perceptron, Random Forest and Support Vector Machine and Decision Tree CART. In a first stage, the areas with torrentiality were digitized based on orthophotomaps and field observations. These regions, together with an equal number of non-torrential pixels, were further divided into training surfaces (70%) and validating surfaces (30%). The next step of the analysis consisted of the selection of flash-flood conditioning factors based on the multicollinearity investigation and predictive ability estimation through Information Gain method. Eight factors, from a total of ten flash-floods predictors, were selected in order to be included in the FFPI calculation process. By applying the models represented by Statistical Index and its ensemble with the machine learning algorithms, the weight of each conditioning factor and of each factor class/category in the FFPI equations was established. Once the weight values were derived, the FFPI values across the Bâsca Chiojdului river basin were calculated by overlaying the flash-flood predictors in GIS environment. According to the results obtained, the central part of Bâsca Chiojdului river basin has the highest susceptibility to flash-flood phenomena. Thus, around 30% of the study site has high and very high values of FFPI. The results validation was carried out by applying the Prediction Rate and Success Rate. The methods revealed the fact that the Multilayer Perceptron - Statistical Index (MLP-SI) ensemble has the highest efficiency among the 3 methods.

A Depression-Based Index to Represent Topographic Control in Urban Pluvial Flooding

Extensive studies have highlighted the roles of rainfall, impervious surfaces, and drainage systems in urban pluvial flooding, whereas topographic control has received limited attention. This study proposes a depression-based index, the Topographic Control Index (TCI), to quantify the function of topography in urban pluvial flooding. The TCI of a depression is derived within its catchment, multiplying the catchment area with the slope, then dividing by the ponding volume of the depression. A case study is demonstrated in Guangzhou, China, using a 0.5 m-resolution Digital Elevation Model (DEM) acquired using Light Detection and Ranging (LiDAR) technology. The results show that the TCI map matches well with flooding records, while the Topographic Wetness Index (TWI) cannot map the frequently flooded areas. The impact of DEM resolution on topographic representation and the stability of TCI values are further investigated. The original 0.5 m-resolution DEM is set as a baseline, and is resampled at resolutions 1, 2, 5, and 10 m. A 1 m resolution has the smallest TCI deviation from those of 0.5 m resolution, and gives the optimal results in terms of striking a balance between computational efficiency and precision of representation. Moreover, the uncertainty in TCI values is likely to increase for small depressions.

A Geospatial Assessment of Flood Vulnerability Reduction by Freshwater Wetlands-A Benefit Indicators Approach

Flooding is among the most common and costly natural disasters in the United States. Flood impacts have been on the rise as flood mitigating habitats are lost, development places more people and infrastructure potentially at risk, and changing rainfall results in altered flood frequency. Across the nation, communities are recognizing the value of flood mitigating habitats and employing green infrastructure alternatives, including restoring some of those ecosystems, as a way to increase resilience. However, communities may under value green infrastructure, because they do not recognize the current benefits of risk reduction they receive from existing ecosystems or the potential benefits they could receive through restoration. Freshwater wetlands have long been recognized as one of the ecosystems that can reduce flood damages by attenuating surface water. Small-scale community studies can capture the flood-reduction benefits from existing or potentially restored wetlands. However, scalability and transferability are limits for these high resolution and data intensive studies. This paper details the development of a nationally consistent dataset and a set of high-resolution indicators characterizing where people benefit from reduced flood risk through existing wetlands. We demonstrate how this dataset can be used at different scales (regional or local) to rapidly assess flood-reduction benefits. At a local scale we use other national scale indicators (CRSI, SoVI) to gauge community resilience and recoverability to choose Harris County, Texas as our focus. Analysis of the Gulf Coast region and Harris County, Texas identifies communities with both wetland restoration potential and the greatest flood-prone population that could benefit from that restoration. We show how maps of these indicators can be used to set wetland protection and restoration priorities.

Assessment of urban flood susceptibility using semi-supervised machine learning model

In order to identify flood-prone areas with limited flood inventories, a semi-supervised machine learning model-the weakly labeled support vector machine (WELLSVM)-is used to assess urban flood susceptibility in this study. A spatial database is collected from metropolitan areas in Beijing, including flood inventories from 2004 to 2014 and nine metrological, geographical, and anthropogenic explanatory factors. Urban flood susceptibility is mapped and compared using logistic regression, artificial neural networks, and a support vector machine. Model performances are evaluated using four evaluation indices (accuracy, precision, recall, and F-score) as well as the receiver operating characteristic curve. The results show that WELLSVM can better utilize the spatial information (unlabeled data), and it outperforms all comparison models. The high-quality WELLSVM flood susceptibility map is thus applicable to efficient urban flood management.