Related Experiment Video
Updated: Sep 2, 2025
08:56
Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates
Published on: January 13, 2023
2.3K
Decoding river pollution trends and their landscape determinants in an ecologically fragile karst basin using a
Guoyu Xu1, Hongxiang Fan1, David M Oliver2
1Key Laboratory of Watershed Geographic Sciences, Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences, Nanjing, 210008, China; University of Chinese Academy of Sciences, Beijing, 100049, China.
Environmental Research
|August 5, 2022
Summary
Machine learning predicts water quality in fragile karst watersheds, identifying agricultural runoff and soil properties as key pollution drivers. This helps target restoration efforts in complex environments.
Area of Science:
- Environmental Science
- Hydrology
- Geochemistry
Background:
- Karst watersheds exhibit complex landscapes influenced by human and natural activities, impacting water quality, nutrient cycling, and contaminant transport.
- Traditional water quality monitoring is limited by cost and labor, restricting spatial assessments, especially in heterogeneous karst regions.
- Geographical catchment characteristics are crucial but often overlooked factors influencing water quality in karst environments.
Purpose of the Study:
- To develop a machine learning model for predicting the spatial distribution of water quality in a fragile karst watershed.
- To identify key determinants of river water quality impairments using interpretable AI methods.
- To support water quality restoration decision-making by providing spatially explicit data.
Main Methods:
- Applied Extreme Gradient Boosting (XGBoost) to predict spatial water quality distribution.
- Utilized Shapley Additive Explanations (SHAP) to interpret model predictions and identify pollutant drivers.
- Evaluated water quality impairment using the Water Quality Damage Index (WQI-DET), focusing on CODMn, TN, and TP.
Main Results:
- The XGBoost model demonstrated strong performance in predicting water quality parameters (CODMn, TN, TP) across the watershed.
- Predicted ranges: CODMn (1.39–17.40 mg/L), TP (0.02–1.31 mg/L), and TN (0.25–5.72 mg/L).
- SHAP analysis identified anthropogenic sources (agriculture), fragile soil properties (low carbon, high permeability), and transport mechanisms (TWI, carbonate rocks) as primary drivers of pollution.
Conclusions:
- Machine learning, specifically XGBoost with SHAP interpretation, effectively predicts and explains spatial water quality variations in karst watersheds.
- Agricultural pollution, soil characteristics, and hydrological factors significantly contribute to water quality impairments in the study area.
- The study provides crucial data and insights for targeted water quality management and policy development in karst regions.
Keywords:
Determinant analysisEcologically fragile karst basinShapley additive explanationsWater quality assessmentXGBoost regressionMore Related Videos
09:44Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon
Published on: October 16, 2018
10.3K
08:09Measuring and Mapping Patterns of Soil Erosion and Deposition Related to Soil Carbonate Concentrations Under Agricultural Management
Published on: September 12, 2017
11.9K
Related Concept Videos
01:17Design Example: Analyzing Capacity Contours for Flood Risk Assessment
95
Flood risk assessment involves careful planning and analysis to ensure the safety of communities near water retention structures. Capacity contours are a vital tool in this process, as they illustrate the potential spread of water at specific levels in a given area. In the context of building a bund across a small valley, these contours play a critical role in evaluating the safety of nearby residential areas.In this example, the bund is intended to store stormwater in the valley. The engineers...
95
01:30Typical Model Studies
433
Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.
433
01:24Rapidly Varying Flow
132
Rapidly varying flow (RVF) in open channels is characterized by abrupt changes in flow depth over a short distance, with the rate of depth change relative to distance often approaching unity. These flows are inherently complex due to their transient and multi-dimensional nature, making exact analysis difficult. However, approximate solutions using simplified models provide valuable insights into their behavior.Key Features of Rapidly Varying FlowRVF is commonly observed in scenarios involving...
132
02:31Habitat Fragmentation
17.8K
Habitat fragmentation describes the division of a more extensive, continuous habitat into smaller, discontinuous areas. Human activities such as land conversion, as well as slower geological processes leading to changes in the physical environment, are the two leading causes of habitat fragmentation. The fragmentation process typically follows the same steps: perforation, dissection, fragmentation, shrinkage, and attrition.
17.8K
01:18Steps in Outbreak Investigation
176
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
176
01:29Applications of GIS: Disaster Management and Emergency Response
143
Geographic Information System (GIS) technology is essential for risk identification, action prioritization, and resource optimization in critical situations like flooding and earthquakes. By integrating spatial and demographic data, GIS provides a comprehensive framework for emergency response.GIS integrates data layers, like rainfall intensity, topography, elevation profiles, and river levels, to model high-risk flood zones. These layers assess areas susceptible to flooding based on their...
143