<p>Surface water (SW) contamination and vulnerability in urbanized areas have become significant environmental issues that need to be addressed immediately and consistently. More accuracy in prediction models is needed to help with surface water irrigation suited for agriculture. This is a fresh idea that will help with future research in the area and how other areas may be fitted. Urbanization, industrialization, and agriculture are examples of land use patterns that can introduce pollutants into the surface water system, deteriorate its quality, and pose a serious threat to fast expanding cities. As such, they require effective management and intervention techniques.&#xa0;Therefore, this study aimed to map surface water quality (WQ) by adapting integrated multiproxy methods, that were employed to assess if surface water was suitable for use in agriculture. Here, we integrate Artificial Neural Network (ANN), Random Forest (RF), and Support Vector Machine (SVM) models to forecast the suitability of surface water for irrigation in the chosen Mahanadi River Basin, Odisha. This paper introduces an investigated study, that involves nine water samples, gathered from 19 sampling places, classified for a duration of 2017–2023 (6&#xa0;years). A Geographical Information System (GIS) was performed using an Inverse Distance Weighted (IDW) interpolation method, to evaluate the region's surface water governance and provide appropriate management techniques. On this basis, nine surface water samples were collected from nineteen survey stations and further, evaluated by implementing standard methods.&#xa0;The concentration of cations found in the research region, is exhibited as: Mg²⁺ &gt; Ca²⁺ &gt; Na⁺ &gt; K⁺. Based on the results obtained by SAR, the surface water potential zone was classified to be potable for irrigation. In addition to % Na, 42% of the locations belong to the acceptable, and 10.52% represents questionable WQ. The KR shows that 84.21% samples collected during the pre-monsoon season, fall into the excellent category, and possibly, suitable for irrigation. In case of SSP, the 4 samples indicate high Na⁺ content, thus, lowers the infiltration capacity rate. Considering the MAR value, 10.52% of sites, affects the structure of the soil by changing the chemical characteristics of the soil to make it more alkaline. The PS values ranged from 0.13 to 10, in the current study. Again, the highest saline surface water is noticed at V-(9). This is brought about by variances and notable distinctions that are brought about by both anthropogenic and physical factors. Estimating irrigation parameters showed that the model as a whole did a good job of predicting irrigation suitability. However, there was a noticeable resemblance in the outcomes when it came to the sampling locations' prioritization.&#xa0;Meanwhile, as per the outcomes of RMSE, MAPE, and R², the model SVM fared better than ANN and RF. Since ANN, RF, and SVM modeling approaches yield positive and reliable results, current research suggests merging them with surface water suitability for irrigation forecasts. Future researchers will greatly benefit from the study's findings since they will cut down on the cost and duration of analysis by employing ANN, RF, and SVM algorithms to forecast if surface water for irrigation is appropriate. The current study can be used using comparable techniques both locally and worldwide. Hence, it can be concluded that using all three strategies at once gives a solid foundation for creating the WQ outcomes in the chosen river basin.&#xa0;Furthermore, the analysis found governance deficiencies in the region, which increased the vulnerability of surface water due to insufficient monitoring procedures, low institutional capacity, low awareness, and ineffective application of rules and regulations. To address these challenges, according to the study, surface water management requires a multimodal strategy that incorporates socioeconomic, cultural, and technical elements. The fastest-growing region can work toward the sustainable management of its surface water resources through cooperative efforts, legislative changes, community involvement, and efficient enforcement.</p> Graphical Abstract <p></p>