Basin Scale Research Articles

Water Quality Prediction Based on an Innovated Physical and Data Driving Hybrid Model at Basin Scale

The prediction of basin water quality has become an urgent need for water environment management, where water pollution is on the increase. Currently, physical models are primarily used for water quality predictions, but the models are not adaptable for the automatic future prediction of watershed water quality owing to their non-automatic boundary setting. The development of big data, which has led to artificial intelligence (AI) technology, has remedied the deficiency of physical models and has been widely used in water quality prediction. However, the accuracy of AI models depends only on the quantity and quality of dataset, which is applied on specific and discrete sections with enough data and difficult to extend to regions with limited monitoring data. Thus, we constructed migration and distribution gates to express the spatial influence of different variables from different sections on the water quality of a specific and discrete section. The temporal processes were expressed by degradation equation. The migration gate, distribution gate and degradation equations were incorporated into Long Short-Term Memory Network (LSTM) to improve the operation mechanism of the LSTM algorithm to create the Im-LSTM model, which considers both the temporal influence of a specific section and the spatial influence of other sections on a specific section at basin scale. Compared to ANN, LSTM, Im-LSTM showed the best performance for basin water quality prediction, especially for mainstream sections at sudden pollution process. Thus, the proposed Im-LSTM provides a new approach for water environment supervision.

Modelagem integrada de qualidade e quantidade para gestão de recursos hídricos: estudo de caso na Bacia do Alto Paranapanema

ABSTRACT This study introduces an integrated model for water resources planning and management that accounts for both the quantity and quality of water in watersheds and reservoirs. Therefore, it provides a comprehensive approach for better understanding and assessing water systems. The model facilitates analyses of the spatial and temporal dynamics of hydrological processes, pollutant transport, and the behavior of rivers and reservoirs. The study evaluated pollutant load transport in the Upper Paranapanema Basin by applying the Soil Moisture Accounting Procedure (SMAP) model, Muskingum method, Streeter-Phelps buildup/washoff model, and zero-dimensional (0D) models to estimate inflows to the Jurumirim reservoir. A Python-based public library was developed to model all hydrological processes. The model calibration yielded a NSE, KGE, PBIAS and RMSE result of 0.746, 0.778, 6.5% and 73.3 m 3 s − 1, respectively. Indicating a robust simulation that attests to the versatility and reliability of the proposed approach. The methodology outlined in this research enables comprehensive water quality simulation at basin scale, thereby serving as a tool for understanding water quantity and quality dynamics and support decision-making regarding water resource planning and management.

Designing innovative spatial strategies to control black leaf streak disease of banana through modelling approach

Experimentations to evaluate spatial strategies at the scale of a production basin to control Black leaf streak disease (BLSD) is difficult to implement. Modelling is a key approach to identify innovative scenarios to reduce the use of pesticides while efficiently and sustainably controlling the disease. To achieve this aim, we assess the efficacy of strategies directly based on fungicide applications or based on the deployment of resistant cultivars. For that, we adapted a published spatially-explicit model to simulate BLSD epidemics in a real 300-ha agricultural landscape of Costa-Rica. More than 11,000 simulations of strategies are undergoing and the best scenarios will be identified to be further tested in the field.

Seasonal and ocean basin scale variation in the food web baseline and trophic ecology of a wide-ranging Southern Ocean predator derived from amino acid δ15N trends

Seasonal and ocean basin scale variation in the food web baseline and trophic ecology of a wide-ranging Southern Ocean predator derived from amino acid δ15N trends

Integrated mapping of ecosystems and assessment of forest ecosystem services at river basin scale

Ecosystems provide various goods and services to society and their valuation is among the main objectives of the concept of ecosystem services (ES). The mapping of ecosystems is the main building block of the whole process of the Mapping and Assessment of Ecosystems and their Services (MAES). The analyses of the ecosystem data produced during the implementation of the national methodology for mapping ecosystems in Bulgaria (MAES BG) reveal some problems that may cause confusion in cases of integrated assessment of all ecosystem types. In this paper, we present an approach that enables formulation of a uniform spatial dataset based on the mapping of the main ecosystem types, that can be used for mapping of ES at a river basin scale. It has been applied to the upper part of the Ogosta River basin and the result is a topologically correct uniform spatial data layer. The approach gives one possible solution to problems related to the different sources of information and the discrepancies between ecosystem types in the national mapping of ecosystems in Bulgaria. It is based on the use of a uniform spatial framework that outlines the ecosystem types and sets the initial database for further mapping. This ensures a topologically correct spatial dataset for the ecosystems and a background for further updates for each ecosystem at the different levels of MAES typology. The most appropriate spatial basis for the territory of Bulgaria is the database for the physical blocks of the Ministry of Interior. Its application to the studied river basin gives encouraging results and can be used as an example for similar areas. Further development of the approach will ensure the mapping of the forest ecosystems at level 3 of the MAES BG typology and more precise delineation of the grassland, heathland, freshwater, and sparsely vegetated ecosystems.

Ecosystem accounting for water resources at the catchment scale, a case study for the Peloponnisos, Greece

The System of Environmental-Economic Accounts - Ecosystem Accounting (SEEA EA) has become the world’s leading natural capital accounting system. It provides a valuable decision-making tool for spatial planning and integrated development. SEEA implementation is a current key challenge for European Union (EU) Member States (MS), mainly due to high requirements on budget, technical capacity, and data, varying between countries. Within this frame, the objective of this paper is to demonstrate how the SEEA framework can be applied to analyse water ecosystems at river basin scale, building exclusively upon the officially registered, standardized national and EU datasets. We test how water resources can be accounted for using SEEA EA, with an additional component assessing water use based on SEEA Water. Within the EU Water Framework Directive (WFD), two reporting cycles of river basin management plans have been completed for water ecosystems, providing spatial and temporal datasets. This material together with numerous data available at EU and national levels, water-relevant databases and repositories, resulting from MS reporting obligations, are tested and utilised for water accounting. The Alfeios river basin in Western Peloponnisos Greece serves as the case study area for compiling extent accounts, condition accounts, and supply and use accounts for provisioning water ecosystem services (drinking and irrigation water) for the periods 2009–2015 and 2015–2021 (the two WFD reporting cycles). It is demonstrated that readily available EU datasets can support the initial mapping and compiling of water ecosystem accounts at local scale, as applied in Greece, and therefore potentially also in other EU countries with fragmented data scattered in various administrative services and authorities with overlapping responsibilities on water resources. It is also concluded that future WFD reporting cycles and revisions of the river basin management plans could be better structured to enable a more direct connection of the collected data to ecosystem accounts.

Analysis of the effect of rainfall center location on the flash flood process at the small basin scale

Abstract With the increasing frequency of extreme convective weather, the spatial–temporal variability of rainfall becomes more diversified. As a result of the insufficient quality of rainfall monitoring data in mountainous areas, the flash flood simulation usually does not consider the effect of the rainfall center location. In this work, the GPU Accelerated Surface Water Flow and Associated Transport hydrodynamic model is used to simulate the flash flood discharge process. The effect of the rainfall center location and the basin scale on the discharge process were analyzed based on simulated data. The results show that when the rainfall center is in the upstream and midstream basins, because of gravitational potential energy conversion, the total flood volume and the flood peak discharge increase to 2–10 times, and the peak time of flash flood caused by 100 mm rainfall amount can be advanced by up to 3,000 s compared to the 20 mm rainfall amount condition. The peak discharge and the delay of peak time increase with the increase of rain peak coefficient. In addition, the increase of the basin area enhances the effect of the rainfall center location. This work is helpful to quantify the effect of the rainfall center location, which can clarify the uncertainty of flash flood simulation caused by not considering the rainfall center factor.

Synergy Assessment of River Health Values from a Symbiotic Perspective: A Case Study of the Yellow River Basin in China

Rivers are important carriers of water transmission, water supply, and water nourishment, and the virtuous cycle of their ecosystems is directly related to the degree of completion of the construction of ecological civilization and the high-quality development of the national economy. From the perspective of symbiosis theory, this paper constructs a river health value assessment index system and analyzes the symbiotic synergistic effect of nine provinces in the Yellow River Basin in China from 2000 to 2020 by using a logistic symbiosis evolution model. Health values at the Yellow River Basin scale and the provincial administrative area scale were also analyzed, and it was found that (1) the Yellow River Basin experienced a period of sub-par river health in the past, but with the implementation of ecological protection and high-quality development strategy in recent years, the health of the river showed an trend of improvement during the period of 2017–2020; (2) at the provincial administrative scale, the Yellow River Basin has significant differences, which are manifested in the obvious differences between provinces in terms of the functional value of river health provision and the economic functional value. In order to reduce the regional differences, it is recommended that the provinces work together and give full play to their own characteristics and strengths in the management of the watershed, so as to make up for the weaknesses of regional development and realize the synergistic development of the watershed; and (3) in terms of symbiosis level, rivers in the Yellow River Basin generally show parasitic relationships, and most of them exhibit natural ecological diversity and competitiveness with socio-economics. Therefore, a more comprehensive consideration of the balanced development of each function is needed in river health management in the future to achieve integrated watershed health. These results suggest that the development of river ecological health in the Yellow River Basin requires the joint efforts of the whole of society as well as regional synergy and integrated management at the policy level to achieve more sustainable and balanced watershed development.

Good eutrophication status is a challenging goal for coastal waters

Our objective is to understand the effectiveness of local and international nutrient pollution mitigation efforts when targeting better water quality in the region’s coastal waters. To this end, we developed an integrated modeling framework for the Archipelago Sea located in the Baltic Sea in Northern Europe, conducted what-if analyses for various ambition levels of nutrient abatement, and studied the long-term consequences at the sea basin scale. We demonstrate that in outer parts of the Archipelago Sea, a good eutrophication status can be achieved if the current internationally agreed policy goals for nutrient abatement are successfully met. In inner coastal areas, current goals for phytoplankton biomass could be reached only through extreme mitigation efforts in all polluting sectors and large-scale application of yet poorly tested ecological engineering methods. This result calls for carefully considering the relevance of current threshold values for phytoplankton and its role as a dominant indicator of good ecological status.

Rapid mass losses of Urumqi River Basin glaciers, eastern Tianshan Mountains revealed from multi-temporal DEMs, 1964–2021

ABSTRACT Glacier volume changes have remarkable impacts on regional water resources; however, their estimation uncertainties remain large. In this study, the surface elevations of seven glaciers at the headwaters of the Urumqi River exhibited obvious thinning at the rate of 0.32 m a−1 from 1964 to 2021. Correlations between the ice volume change (dV) derived from surface elevation conversion and the area change (dS) were established for valley, cirque, and hanging glaciers. The ice volumes of valley, cirque, and hanging glaciers in the Urumqi River Basin decreased by 0.99 km3, 0.18 km3, and 0.59 km3, respectively, and the total ice volume decreased by 1.76 km3 during 1964–2021. Ice volume losses are accelerating. The correlation between dV and dS for valley glaciers produced a large estimation difference for the ice volume change of Urumqi Glacier No. 1 (UG1) compared with the glaciological mass balance (15%), while the estimation differences of ice volume changes for the three types of glaciers in the Urumqi River Basin were within acceptable limits (10%) based on the geodetic results. This new method has vast potential in estimating ice volume changes at the basin or regional scale, or even across western China.

Impact of Spatial Rainfall Scenarios on River Basin Runoff Simulation a Nan River Basin Study Using the Rainfall-Runoff-Inundation Model

This study aims to investigate the impact of spatial rainfall distribution scenarios from ground observation stations on runoff simulation using hydrological modeling specific to the Rainfall-Runoff-Inundation (RRI) model. The RRI model was applied with six different spatial distribution scenarios of input rainfall, including Inverse Distance Weight (IDW), Thiessen polygon (TSP), Surface Polynomial (SPL), Simple kriging (SKG), and Ordinary kriging (OKG), to simulate the runoff of a 13,000 km2 watershed, namely the Nan River Basin in Thailand. This study utilized data from the 2014 storm event, incorporating temporal information from 28 rainfall stations to estimate rainfall in the spatial distribution scenarios. The six statistics, Volume Bias, Peak Bias, Root Mean Square Error, Correlation, and Mean Bias, were used to determine the accuracy of the estimated rainfall and runoff. Overall, the Simple kriging (SKG) method outperformed the other scenarios based on the statistical values to validate with measured rainfall data. Similarly, SKG demonstrated the closest match between simulated and observed runoff, achieving the highest correlation (0.803), the lowest Root Mean Square Error (164.48 cms), and high Nash-Sutcliffe Efficiency coefficient (0.499) values. This research underscores the practical significance of spatial interpolation methods, such as SKG, in combination with digital elevation models (DEMs) and landuse/soil type datasets, in delivering reliable runoff simulations considering the RRI model on the river basin scale.

Basin Scale Soil Moisture Estimation with Grid SWAT and LESTKF Based on WSN.

This research utilized in situ soil moisture observations in a coupled grid Soil and Water Assessment Tool (SWAT) and Parallel Data Assimilation Framework (PDAF) data assimilation system, resulting in significant enhancements in soil moisture estimation. By incorporating Wireless Sensor Network (WSN) data (WATERNET), the method captured and integrated local soil moisture characteristics, thereby improving regional model state estimations. The use of varying observation search radii with the Local Error-subspace Transform Kalman Filter (LESTKF) resulted in improved spatial and temporal assimilation performance, while also considering the impact of observation data uncertainties. The best performance (improvement of 0.006 m3/m3) of LESTKF was achieved with a 20 km observation search radii and 0.01 m3/m3 observation standard error. This study assimilated wireless sensor network data into a distributed model, presenting a departure from traditional methods. The high accuracy and resolution capabilities of WATERNET's regional soil moisture observations were crucial, and its provision of multi-layered soil temperature and moisture observations presented new opportunities for integration into the data assimilation framework, further enhancing hydrological state estimations. This study's implications are broad and relevant to regional-scale water resource research and management, particularly for freshwater resource scheduling at small basin scales.

Extreme waves in the Caribbean Sea: spatial regionalization and long-term analysis

The extreme wave height distribution in the Caribbean Sea is studied using a new method based on the maximum basin-wide aggregate of significant wave height, Hs, values per month. Besides, by means of the Self-Organizing Maps (SOM) technique, we identify coherent geographical regions with similar extreme wave height variability in the Caribbean Sea. Our findings revealed three primary regions: the eastern side with comparatively lower values, the central region with intermediate values, and the western side with the highest extreme wave heights. The study also examines the wind forcing conditions driving the spatial and temporal variability of the extreme waves, highlighting the influence of the low-pressure belt dynamics as well as the role played by the Caribbean Low-Level Jet (CLLJ) index, and the impact of cold fronts and hurricanes on extreme wave heights. Additionally, we explore the relationship between the extreme wave height distribution and climatic indices, such as the Atlantic Multidecadal Oscillation (AMO), the Atlantic Meridional Mode (AMM), the North Atlantic Oscillation (NAO) and the Oceanic Niño (ONI). The results reveal that the spatial distribution of extreme wave heights in the Caribbean Sea is mostly ruled by the influence of the CLLJ, with correlations close to 80%. In addition, significant correlations were observed between the extreme wave heights and the ENSO in the central Caribbean, as well as positive correlations between the extreme wave heights and NAO in the eastern part of the basin, and significant values of correlation with the negative phases of AMO and AMM in the whole basin. We show that, unlike conventional (or broadly used) methods deployed to identify extreme wave height, such as percentile 99th, Hs99, our methodology allows a further assessment of the wind and climate forcing conditions associated with the extreme wave events. Although, we acknowledge that the method here presented has limitations to capture extreme wave height outliers, it has the advantage of being used concomitant with the wind forcing to develop multivariate wave climate analysis at basin scale, and could be extended to a more local scale when studying coastal processes.

First basin scale spatial–temporal characterization of underwater sound in the Mediterranean Sea

Anthropogenic underwater noise is an emergent pollutant. Despite several worldwide monitoring programs, only few data are available for the Mediterranean Sea, one of the global biodiversity hotspots. The results of the first continuous acoustic programme run at a transnational basin scale in the Mediterranean Sea are here presented. Recordings were done from March 2020 to June 2021, including the COVID-19 lockdown, at nine stations in the Northern Adriatic Sea. Spatial–temporal variations of the underwater sound are described, having one third octave band sound pressure levels (SPLs) from 10 Hz to 20 kHz as metrics. Higher and more variable SPLs, mainly related to vessel traffic, were found close to harbours, whereas Natura 2000 stations experienced lower SPLs. Lower values were recorded during the lockdown in five stations. Median yearly SPLs ranged between 64 and 95 as well as 70 and 100 dB re 1 µPa for 63 and 125 Hz bands, respectively. These values are comparable with those previously found in busy shallow EU basins but higher levels are expected during a business-as-usual period. This is a baseline assessment for a highly impacted and environmental valuable area, that needs to be managed in a new sustainable blue growth strategy.

Long-term gridded land evapotranspiration reconstruction using Deep Forest with high generalizability

Previous datasets have limitations in generalizing evapotranspiration (ET) across various land cover types due to the scarcity and spatial heterogeneity of observations, along with the incomplete understanding of underlying physical mechanisms as a deeper contributing factor. To fill in these gaps, here we developed a global Highly Generalized Land (HG-Land) ET dataset at 0.5° spatial resolution with monthly values covering the satellite era (1982–2018). Our approach leverages the power of a Deep Forest machine-learning algorithm, which ensures good generalizability and mitigates overfitting by minimizing hyper-parameterization. Model explanations are further provided to enhance model transparency and gain new insights into the ET process. Validation conducted at both the site and basin scales attests to the dataset’s satisfactory accuracy, with a pronounced emphasis on the Northern Hemisphere. Furthermore, we find that the primary driver of ET predictions varies across different climatic regions. Overall, the HG-Land ET, underpinned by the interpretability of the machine-learning model, emerges as a validated and generalized resource catering to scientific research and various applications.

Hydrologic signature of intermittent channel networks in small-scale river basin

This study aims to figure out the recession flow patterns embedded in the hydrologic data in terms of the geomorphologic features of river basins. To this end, based on the scaling relation of channel networks to source basin areas, we modify the geomorphologic recession flow model originated by Biswal and Marani (2010), and verify its validity through power law distribution of drainage areas and Hack’s law. There exists a distinct difference in the recession flow patterns between the whole body of data and the individual event data for the basin of interest, and the latter tends to have a similar pattern in common at the different scales of discharges. Both geomorphologic recession flow models reflect the recession flow patterns in the hydrologic data. The maximum likelihood method produces reliable estimates of the lower limit of mass aggregation patterns in river basins. The exponentially tempered power law distribution gives rise to very similar results to the scaling relation of channel networks to source basin areas. The recession flow patterns of the basin of interest could be reflected in the behavior of intermittent channel networks which follows the fractal nature of fluvial processes. The inconsistent recession flow patterns inferred from Hack’s law could be attributed to the spatial scale of the basin, implying that Hack’s law might have a valid domain at a larger scale than the basin of interest. Nevertheless, consistent trends could be found between the power law distribution of drainage areas and the scaling relations of channel networks to source basins areas, which are directly related to Horton ratios and the fractal dimensions. So, the geomorphologic recession flow model modified in this study could be a useful tool to analyze the recession flow pattern for river basins regardless of the basin scale.

A new framework for evaluating water use reduction strategies using an integrated, holistic, and transparent approach (Urmia Lake basin case study)

Agriculture and food security have always faced challenges related to water scarcity, so agricultural water conservation is the most important strategy for overcoming this challenge. In this study, the REWAS tool developed by FAO and Future Water was used to evaluate the effects of technological and management strategies on real water savings (RWS) in the Zarrineh River sub-basin, Iran. Nine farms were investigated (wheat, corn, tomato, sugar beet), including control and treatment farms. According to changes in water consumption and return flows, RWS was calculated for various scenarios of field interventions. To assess the water consumption in Basin scale, REWAS was simplified the accounting framework for water consumption (consumed and unconsumed). In the Zarrineh River sub-basin, the use of the techniques applied in the treatment farm, compared to the control farm (according to farmer customary practices), resulted in a significant reduction of non-beneficial consumption. For example, according to the REWAS evaluation in West s17 farn, the treatment farm consumed the most useful water compared to the control farm (331 mm and 267 mm, respectively), which led to the most useful water consumption at basin scale (to the order of 3920 mm and 3166 mm). According to the results on the scale of the basin , the highest amount of recoverable discharge was also obtained in the control farm with an increase of 3774 MCM over the treatment farm. Using strategies to reduce water consumption resulted in apparent water saving (AWS) at the farm scale, but these AWS were very different from their RWS at the basin scale and the RWS at the basin scale (13%) was much lower than the AWS at the farm scale (38%). According to the results, apparent water savings (AWS) at the farm scale do not reduce water consumption, and may actually increase it when viewed in a basin scale. REWAS concepts indicate that significant amounts of “lost” water are actually recoverable return flows that can be used by downstream users or contribute to wetlands. According to REWAS concepts, real water savings can only be achieved by preventing non-recyclable backflows. Assessing RWS can help decision makers select sustainable interventions that will improve agricultural water productivity by providing information on farm flows, irrigation networks, and basin scales.

Radiative Impacts of Californian Marine Low Clouds on North Pacific Climate in a Global Climate Model

Abstract The northeastern Pacific climate system features an extensive low-cloud deck off California on the southeastern flank of the subtropical high that accompanies intense northeasterly trades and relatively low sea surface temperatures (SSTs). This study assesses climatological impacts of the low-cloud deck and their seasonal differences by regionally turning on and off the low-cloud radiative effect in a fully coupled atmosphere–ocean model. The simulations demonstrate that the cloud radiative effect causes a local SST decrease of up to 3°C on an annual average with the response extending southwestward with intensified trade winds, indicative of the wind–evaporation–SST (WES) feedback. This nonlocal wind response is strong in summer, when the SST decrease peaks due to increased shortwave cooling, and persists into autumn. In these seasons when the background SST is high, the lowered SST suppresses deep-convective precipitation that would otherwise occur in the absence of the low-cloud deck. The resultant anomalous diabatic cooling induces a surface anticyclonic response with the intensified trades that promote the WES feedback. Such seasonal enhancement of the atmospheric response does not occur without air–sea couplings. The enhanced trades accompany intensified upper-tropospheric westerlies, strengthening the vertical wind shear that, together with the lowered SST, acts to shield Hawaii from powerful hurricanes. On the basin scale, the anticyclonic surface wind response accelerates the North Pacific subtropical ocean gyre to speed up the Kuroshio by as much as 30%. SST thereby increases along the Kuroshio and its extension, intensifying upward turbulent heat fluxes from the ocean to increase precipitation.

Comprehensive evaluation of antibiotics pollution the Yangtze River basin, China: Emission, multimedia fate and risk assessment

Antibiotics have attracted global attention because of their potential ecological and health risks. The emission, multimedia fate and risk of 18 selected antibiotics in the entire Yangtze River basin were evaluated by using a level Ⅳ fugacity model. High antibiotic emissions were found in the middle and lower reaches of the Yangtze River basin. The total antibiotic emissions in the Yangtze River basin exceeded 1600 tons per year between 2013 and 2021. The spatial distribution of antibiotics concentration was the upper Yangtze River > middle Yangtze River > lower Yangtze River, which is positively correlated with animal husbandry size in the basin. Temperature and precipitation increases may decrease the antibiotic concentrations in the environment. Transfer fluxes showed that source emission inputs, advection processes, and degradation fluxes contributed more to the total input and output. High ecological risks in the water environment were found in 2018, 2019, 2020, and 2021. The comprehensive health risk assessment through drinking water and fish consumption routes showed that a small part of the Yangtze River basin is at medium risk, and children have a relatively high degree of health risk. This study provides a scientific basis for the pollution control of antibiotics at the basin scale.

Machine-Learning-Based Forest Classification and Regression (FCR) for Spatial Prediction of Liver Fluke Opisthorchis viverrini (OV) Infection in Small Sub-Watersheds

Infection of liver flukes (Opisthorchis viverrini) is partly due to their suitability for habitats in sub-basin areas, which causes the intermediate host to remain in the watershed system in all seasons. The spatial monitoring of fluke at the small basin scale is important because this can enable analysis at the level of the factors involved that influence infections. A spatial mathematical model was weighted by the nine spatial factors X1 (index of land-use types), X2 (index of soil drainage properties), X3 (distance index from the road network, X4 (distance index from surface water resources), X5 (distance index from the flow accumulation lines), X6 (index of average surface temperature), X7 (average surface moisture index), X8 (average normalized difference vegetation index), and X9 (average soil-adjusted vegetation index) by dividing the analysis into two steps: (1) the sub-basin boundary level was analyzed with an ordinary least square (OLS) model used to select the spatial criteria of liver flukes aimed at analyzing the factors related to human liver fluke infection according to sub-watersheds, and (2) we used the infection risk positional analysis level through machine-learning-based forest classification and regression (FCR) to display the predictive results of infection risk locations along stream lines. The analysis results show four prototype models that import different independent variable factors. The results show that Model 1 and Model 2 gave the most AUC (0.964), and the variables that influenced infection risk the most were the distance to stream lines and the distance to water bodies; the NDMI and NDVI factors rarely affected the accuracy. This FCR machine-learning application approach can be applied to the analysis of infection risk areas at the sub-basin level, but independent variables must be screened with a preliminary mathematical model weighted to the spatial units in order to obtain the most accurate predictions.