Assessing Climate-Sensitive Nutrient Pollution Hazards in Urban-Rural Transitional Watersheds: An Artificial Intelligence and Remote Sensing Data Assimilation Approach

Abstract

Climate-driven changes in precipitation, temperature, and runoff are intensifying nutrient pollution hazards in watersheds, particularly in urban-rural transitional zones characterized by fragmented land use and sparse monitoring. Predicting these climate-sensitive nonpoint source pollution (NPSP) dynamics is difficult because multisource inputs and rapidly evolving spatial patterns challenge conventional models. This study developed an artificial intelligence (AI) framework that integrates machine learning with remote sensing data assimilation to assess nutrient pollution in rapidly urbanizing basins. A random forest regression model, trained on 15 GIS-based predictors, serves as the core predictor for total nitrogen (TN) and total phosphorus (TP) concentrations. An ensemble Kalman filter (EnKF) assimilates remote sensing inversion (RSI) products into the model for dynamic updates. Applied to the Wenruitang River watershed in eastern China, the framework reduces TP prediction errors by up to 52.9% compared with standalone models and better captures short-term concentration fluctuations relevant for hazard assessment. Shapley additive explanation (SHAP) analysis reveals that socioeconomic and meteorological variables dominate temporal variability, while land-use indicators, specifically construction land and water area, serve as stable spatial drivers of nutrient hazard. Receiver operating characteristic (ROC)-based land-use thresholds identify critical source zones with > 71% construction land or < 5% water area. Although these zones occupy only 26% of the basin, they contain 60% of high-TN hotspot grids and 48% of high-TP hotspot grids. The findings demonstrate that remote sensing-assisted AI can effectively identify nutrient pollution hotspots and offer a transferable, interpretable tool for climate-resilient water quality management and hazard-informed watershed governance.

Keywords

Climate change / Machine learning / Nonpoint source pollution (NPSP) / Nutrient pollution hazard / Remote sensing data assimilation / Urban-rural transitional watersheds

References

[1] AbdelMoez, W., M. Kholief, and F.M. Elsalmy. 2013. Improving bug fix-time prediction model by filtering out outliers. In Proceedings of 2013 International Conference on Technological Advances in Electrical, Electronics and Computer Engineering (TAEECE), 9–11 May 2013, Konya, Turkey, 359–364.

[2] Azad, A., M.N. Sheikh, and F.I. Hai. 2024. A critical review of the mechanisms, factors, and performance of pervious concrete to remove contaminants from stormwater runoff. Water Research 251: Article 121101.

[3] Cai B, Liang S, Zhou J, Wang J, Cao L, Qu S, Xu M, Yang Z. China high resolution emission database (CHRED) with point emission sources, gridded emission data, and supplementary socioeconomic data. Resources, Conservation and Recycling, 2018, 129: 232-239

[4] Chappell NA, Jones TD, Tych W. Sampling frequency for water quality variables in streams: Systems analysis to quantify minimum monitoring rates. Water Research, 2017, 123: 49-57

[5] Chen, K., H. Chen, C. Zhou, Y. Huang, X. Qi, R. Shen, F. Liu, M. Zuo, et al. 2020. Comparative analysis of surface water quality prediction performance and identification of key water parameters using different machine learning models based on big data. Water Research 171: Article 115454.

[6] Chen C, Huang J, Chen Q, Zhang J, Li Z, Lin Y. Assimilating multi-source data into a three-dimensional hydro-ecological dynamics model using ensemble Kalman filter. Environmental Modelling and Software, 2019, 117: 188-199

[7] Chen, J., X. Wang, and F. Lei. 2024. Data-driven multinomial random forest: A new random forest variant with strong consistency. Journal of Big Data 11(1): Article 34.

[8] Chen, W., X. Zhang, N. Wu, C. Yuan, Y. Liu, Y. Yang, Z. Chen, R.A. Dahlgren, et al. 2024. Sources and transformations of riverine nitrogen across a coastal-plain river network of eastern China: New insights from multiple stable isotopes. Science of the Total Environment 924: Article 171671.

[9] Clough J, Polaczyk A, Propato M. Modeling the potential effects of sea-level rise on the coast of New York: Integrating mechanistic accretion and stochastic uncertainty. Environmental Modelling and Software, 2016, 84: 349-362

[10] Dash, S.S., B. Sahoo, and N.S. Raghuwanshi. 2023. Improved drought monitoring in teleconnection to the climatic escalations: A hydrological modeling based approach. Science of the Total Environment 857: Article 159545.

[11] Fang, S., M.J. Deitch, T.G. Gebremicael, C. Angelini, and C.J. Ortals. 2024. Identifying critical source areas of non-point source pollution to enhance water quality: Integrated SWAT modeling and multi-variable statistical analysis to reveal key variables and thresholds. Water Research 253: Article 121286.

[12] Fisher J, Acreman MC. Wetland nutrient removal: A review of the evidence. Hydrology and Earth System Sciences, 2004, 8(4): 673-685

[13] Flanagan DC, Gilley JE, Franti TG. Water Erosion Prediction Project (WEPP): Development history, model capabilities, and future enhancements. Transactions of the ASABE, 2007, 50(5): 1603-1612

[14] Fu, X., X. Song, X. Liu, and M. Zhang. 2023. Distributed state estimation with state equality constraints in the presence of packet dropping. Applied Mathematics and Computation 451: Article 128043.

[15] Gerlein-Safdi C, Keppel-Aleks G, Wang F, Frolking S, Mauzerall DL. Satellite monitoring of natural reforestation efforts in China’s drylands. One Earth, 2020, 2(1): 98-108

[16] Häfliger, V., E. Martin, A. Boone, S. Ricci, and S. Biancamaria. 2019. Assimilation of synthetic SWOT river depths in a regional hydrometeorological model. Water 11(1): Article 78.

[17] He, L., S. Li, C.H. Cui, S.S. Yang, J. Ding, G.Y. Wang, S.W. Bai, L. Zhao, et al. 2022. Runoff control simulation and comprehensive benefit evaluation of low-impact development strategies in a typical cold climate area. Environmental Research 206: Article 112630.

[18] Howarth R, Chan F, Conley DJ, Garnier J, Doney SC, Marino R, Billen G. Coupled biogeochemical cycles: Eutrophication and hypoxia in temperate estuaries and coastal marine ecosystems. Frontiers in Ecology and the Environment, 2011, 9(1): 18-26

[19] Hu, J., and S. Szymczak. 2023. A review on longitudinal data analysis with random forest. Briefings in Bioinformatics 24(2): Article bbad002.

[20] Hu, Y., R. Wei, K. Yu, Z. Liu, Q. Zhou, M. Zhang, C.C. Wang, L. Zhang, et al. 2024. Exploring sludge yield patterns through interpretable machine learning models in China’s municipal wastewater treatment plants. Resources, Conservation and Recycling 204: Article 107467.

[21] Huang, S., J. Xia, Y. Wang, J. Lei, and G. Wang. 2024. Water quality prediction based on sparse dataset using enhanced machine learning. Environmental Science and Ecotechnology 20: Article 100402.

[22] Keller, J., H.J.H. Franssen, and W. Nowak. 2021. Investigating the pilot point ensemble Kalman filter for geostatistical inversion and data assimilation. Advances in Water Resources 155: Article 104010.

[23] Kim, S.H., D.H. Lee, M.S. Kim, H.P. Rhee, J. Hur, and K.H. Shin. 2023. Systematic tracing of nitrate sources in a complex river catchment: An integrated approach using stable isotopes and hydrological models. Water Research 235: Article 119755.

[24] Le, M.H., B.Q. Nguyen, H.T. Pham, A. Patil, H.X. Do, R.A.A.J. Ramsankaran, J.D. Bolten, and V. Lakshmi. 2022. Assimilation of SMAP products for improving streamflow simulations over tropical climate region – Is spatial information more important than temporal information? Remote Sensing 14(7): Article 1607.

[25] Li, S., W. An, J. Zhang, M. Gan, K. Wang, L. Ding, and W. Li. 2023. Optimizing limit lines in urban-rural transitional areas: Unveiling the spatial dynamics of trade-offs and synergies among land use functions. Habitat International 140: Article 102907.

[26] Liu B, Ding M, Shaham S, Rahayu W, Farokhi F, Lin Z. When machine learning meets privacy: A survey and outlook. ACM Computing Surveys (CSUR), 2021, 54(2): 1-36

[27] Liu, J., C. Liu, M. Xiao, M. Li, M. Jiang, S. Wang, L. Yin, and B. Zhang. 2024a. Study on non-point source pollution prevention and control system in Nansi Lake Basin based on system dynamics approach. Sustainability 16(17): Article 7831.

[28] Liu, W., Y. Gao, Y. You, C. Jiang, T. Hua, and B. Xia. 2024b. Adaptive time-step unscented Kalman filtering (ATS-UKF) based observer design for urea selective catalytic reduction (SCR) performance of diesel engines. Journal of Hazardous Materials 468: Article 133712.

[29] Liu, W., S. Park, R.T. Bailey, E. Molina-Navarro, H.E. Andersen, H. Thodsen, A. Nielsen, E. Jeppesen, et al. 2020. Quantifying the streamflow response to groundwater abstractions for irrigation or drinking water at catchment scale using SWAT and SWAT-MODFLOW. Environmental Sciences Europe 32(1): Article 113.

[30] Liu R, Xu F, Zhang P, Yu W, Men C. Identifying non-point source critical source areas based on multi-factors at a basin scale with SWAT. Journal of Hydrology, 2016, 533: 379-388

[31] Luo, C., Z. Li, H. Liu, H. Li, R. Wan, J. Pan, and X. Chen. 2020. Differences in the responses of flow and nutrient load to isolated and coupled future climate and land use changes. Journal of Environmental Management 256: Article 109918.

[32] Ma, L., L. Gutierrez, R. Verbeke, A. D’Haese, M. Waqas, M. Dickmann, R. Helm, I. Vankelecom, et al. 2021. Transport of organic solutes in ion-exchange membranes: Mechanisms and influence of solvent ionic composition. Water Research 190: Article 116756.

[33] Maúre, E.D.R., G. Terauchi, J. Ishizaka, N. Clinton, and M. DeWitt. 2021. Globally consistent assessment of coastal eutrophication. Nature Communications 12(1): Article 6142.

[34] Ouyang W, Guo B, Hao F, Huang H, Li J, Gong Y. Modeling urban storm rainfall runoff from diverse underlying surfaces and application for control design in Beijing. Journal of Environmental Management, 2012, 113: 467-473

[35] Page T, Smith PJ, Beven KJ, Jones ID, Elliott JA, Maberly SC, Mackay EB, De Ville M, et al. . Adaptive forecasting of phytoplankton communities. Water Research, 2018, 134: 74-85

[36] Parsa, A.B., A. Movahedi, H. Taghipour, S. Derrible, and A.K. Mohammadian. 2020. Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis. Accident Analysis and Prevention 136: Article 105405.

[37] Pfannerstill M, Guse B, Reusser D, Fohrer N. Process verification of a hydrological model using a temporal parameter sensitivity analysis. Hydrology and Earth System Sciences, 2015, 19(10): 4365-4376

[38] Rahat, S.H., T. Steissberg, W. Chang, X. Chen, G. Mandavya, J. Tracy, A. Wasti, G. Atreya, et al. 2023. Remote sensing-enabled machine learning for river water quality modeling under multidimensional uncertainty. Science of the Total Environment 898: Article 165504.

[39] Rezaie-Balf, M., N.F. Attar, A. Mohammadzadeh, M.A. Murti, A.N. Ahmed, C.M. Fai, N. Nabipour, S. Alaghmand, et al. 2020. Physicochemical parameters data assimilation for efficient improvement of water quality index prediction: Comparative assessment of a noise suppression hybridization approach. Journal of Cleaner Production 271: Article 122576.

[40] Rodriguez-Galiano V, Mendes MP, Garcia-Soldado MJ, Chica-Olmo M, Ribeiro L. Predictive modeling of groundwater nitrate pollution using Random Forest and multisource variables related to intrinsic and specific vulnerability: A case study in an agricultural setting (Southern Spain). Science of the Total Environment, 2014, 476: 189-206

[41] Roy, A., and S. Chakraborty. 2023. Support vector machine in structural reliability analysis: A review. Reliability Engineering and System Safety 233: Article 109126.

[42] Shi, J., X. Chen, B. Ye, Z. Wang, Y. Sun, J. Wu, and H. Guo. 2023. A comparative study of DNAPL migration and transformation in confined and unconfined groundwater systems. Water Research 245: Article 120649.

[43] Singh R, Tiwari KN, Mal BC. Hydrological studies for small watershed in India using the ANSWERS model. Journal of Hydrology, 2006, 318(1–4): 184-199

[44] Sonobe T, Hu D, Otsuka K. Industrial development in the inland region of China: A case study of the motorcycle industry. Journal of Comparative Economics, 2006, 34(4): 818-838

[45] Sun, H., Y. Tian, L. Li, Y. Meng, X. Huang, W. Zhan, X. Zou, and G. Cai. 2022. Anthropogenic pollution discharges, hotspot pollutants and targeted strategies for urban and rural areas in the context of population migration: Numerical modeling of the Minjiang River basin. Environment International 169: Article 107508.

[46] Tavora, J., B. Jiang, T. Kiffney, G. Bourdin, P.C. Gray, L.S. de Carvalho, G. Hesketh, K.M. Schild, et al. 2023. Recipes for the derivation of water quality parameters using the high-spatial-resolution data from sensors on board Sentinel-2A, Sentinel-2B, Landsat-5, Landsat-7, Landsat-8, and Landsat-9 satellites. Journal of Remote Sensing 3: Article 0049.

[47] Thangavel, K., R. Sabatini, A. Gardi, K. Ranasinghe, S. Hilton, P. Servidia, and D. Spiller. 2024. Artificial intelligence for trusted autonomous satellite operations. Progress in Aerospace Sciences 144: Article 100960.

[48] Wang C, Ma X, Jia L, Lai Z, Yang Z, Yan H, Zhao J. CPS architecture design for urban roadway intersections based on MBSE. Journal of Intelligent and Connected Vehicles, 2024, 7(3): 190-204

[49] Wei, Y., H. Cui, Q. Hu, Y. Bai, K. Qu, J. Sun, and Z. Cui. 2022. Eutrophication status assessment in the Laizhou Bay, Bohai Sea: Further evidence for the ecosystem degradation. Marine Pollution Bulletin 181: Article 113867.

[50] Wei, W., N. Wang, L. Yin, S. Guo, and L. Bo. 2024. Spatio-temporal evolution characteristics and driving mechanisms of urban-agricultural-ecological space in ecologically fragile areas: A case study of the upper reaches of the Yangtze River Economic Belt, China. Land Use Policy 145: Article 107282.

[51] Wu, Z., H. Liang, H. Wu, Z. Xie, H. Liu, J. Zhang, J. Zhu, B. Zheng, et al. 2024. Application of improved risk assessment methods to best management practices research for non-point source pollution: From a hilly mountainous-dominated region of southern China. Ecological Indicators 165: Article 112223.

[52] Västilä, K., and T. Jilbert. 2025. Evaluating multiannual sedimentary nutrient retention in agricultural two-stage channels. Scientific Reports 15(1): Article 722.

[53] Xu, S., G. Liu, and B. Mou. 2023. Vulnerability analysis of land ecosystem considering ecological cost and value: A complex network approach. Ecological Indicators 147: Article 109941.

[54] Xue, J., Q. Wang, and M. Zhang. 2022. A review of non-point source water pollution modeling for the urban-rural transitional areas of China: Research status and prospect. Science of the Total Environment 826: Article 154146.

[55] Xue, J., C. Yuan, X. Ji, and M. Zhang. 2024. Predictive modeling of nitrogen and phosphorus concentrations in rivers using a machine learning framework: A case study in an urban-rural transitional area in Wenzhou China. Science of the Total Environment 910: Article 168521.

[56] Yang, H., J. Kong, H. Hu, Y. Du, M. Gao, and F. Chen. 2022. A review of remote sensing for water quality retrieval: Progress and challenges. Remote Sensing 14(8): Article 1770.

[57] Yang, X., Y. Zhou, X. Yang, Y. Zhang, R.G. Spencer, J.D. Brookes, E. Jeppesen, H. Zhang, et al. 2024. Optical measurements of dissolved organic matter as proxies for CODMn and BOD5 in plateau lakes. Environmental Science and Ecotechnology 19: Article 100326.

[58] Zheng, J., Y. Chen, Z. Wu, Y. Wang, and L. Wang. 2024. Integration of flexible touch panels and machine learning: Applications and techniques. Advanced Intelligent Systems 6(3): Article 2300560.

[59] Zhu P, Shi L, Zhu Y, Zhang Q, Huang K, Williams M. Data assimilation of soil water flow via ensemble Kalman filter: Infusing soil moisture data at different scales. Journal of Hydrology, 2017, 555: 912-925

[60] Zou, Y., Z. Lin, D. Li, and Z. Liu. 2023. Advancements in Artificial Neural Networks for health management of energy storage lithium-ion batteries: A comprehensive review. Journal of Energy Storage 73: Article 109069.

[61] Zou, L., Y. Liu, Y. Wang, and X. Hu. 2020. Assessment and analysis of agricultural non-point source pollution loads in China: 1978–2017. Journal of Environmental Management 263: Article 110400.

RIGHTS & PERMISSIONS

The Author(s)

Just Accepted

This article has successfully passed peer review and final editorial review, and will soon enter typesetting, proofreading and other publishing processes. The currently displayed version is the accepted final manuscript. The officially published version will be updated with format, DOI and citation information upon launch. We recommend that you pay attention to subsequent journal notifications and preferentially cite the officially published version. Thank you for your support and cooperation.