Surface water systems face unprecedented stress due to climate variability, urbanization, land-use change, and growing water demand—prompting a shift from traditional hydrological modeling to intelligent, adaptive systems. This review critically explores the integration of Artificial Intelligence (AI) in surface flow management, encompassing applications in streamflow forecasting, sediment transport, flood prediction, water quality monitoring, and infrastructure operations such as dam and irrigation control. Drawing from over two decades of interdisciplinary literature, this study synthesizes recent advances in machine learning (ML), deep learning (DL), the Internet of Things (IoT), remote sensing, and hybrid AI–physics models. Unlike earlier reviews focusing on single aspects, this paper presents a systems-level perspective that links AI technologies to their operational, ethical, and governance dimensions. It highlights key AI techniques—including Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNNs), Graph Neural Networks (GNNs), Transformer models, and Reinforcement Learning—and discusses their strengths, limitations, and implementation challenges, particularly in data-scarce and climate-uncertain regions. Novel insights are provided on Explainable AI (XAI), algorithmic bias, cybersecurity risks, and institutional readiness, positioning this paper as a roadmap for equitable and resilient AI adoption. By combining methodological analysis, conceptual frameworks, and future directions, this review offers a comprehensive guide for researchers, engineers, and policy-makers navigating the next generation of intelligent surface flow management.

The archipelagic Romblon province frequently experiences typhoons and heavy rains that causes extreme flooding, this produces particular concern about the severity of damage in the Municipality of Odiongan. Hence, this study aimed to assess the spatial flood risk of Odiongan using the analytical hierarchy process (AHP), considering disaster risk factors with data collected from various government agencies. The study employed the geographic information system (GIS) to illustrate the spatial distribution of flooding in the municipality. Sendai Framework was the basis of risk analysis in this study. The hazard parameters considered were average annual rainfall, elevation, slope, soil type, and flood depth. Population density, land use, and household number were considered parameters for the exposure assessment. Vulnerability assessments considered gender ratio, mean age, average income, number of persons with disabilities, educational attainment, water usage, emergency preparedness, type of structures, and distance to evacuation area as physical, social, and economic factors. Each parameter was compared to one another by pairwise comparison to identify the weights based on experts’ judgment. These weights were then integrated into the flood risk assessment computation. The results led to a flood risk map which recorded nine barangays (small local government units) at high risk of flooding, notably the Poblacion Area. The results of this study will guide local government units in developing prompt flood management programs, appropriate mitigation measures, preparedness, and response and recovery strategies to reduce flood risk and vulnerability to the population of Odiongan.

Sibuyan Island is experiencing a significant increase in electricity demand due to population growth, urbanization, and industrial development. The island plans to use solar energy, recognizing its abundance and renewable nature; thus, this study was conducted to visualize the spatial distribution of solar exploration suitability using a geographic information system (GIS). Various criteria, including climatology, location, geography, meteorology, and disaster susceptibility, were considered in the assessment. Parameters affected by government policies, such as protected areas, proximity to rivers, roads and faults, ancestral domains, and proclaimed watersheds, were also considered. Parameters were weighted, and suitability levels were highlighted using AHP. The study revealed that about 5.88% (2674.06 km²) of the island was categorized as highly suitable for a solar farm, 34.99% (15,908.21 km²) as suitable, 2.49% (1129.95 km²) as moderately suitable, and the majority, 56.64% (25,754.47 km²), was considered not suitable for solar projects. A solar power suitability map was developed as a reference for local governments and residents in establishing solar PV systems in their respective sites, thus maximizing the full potential of their land. The study also directs future solar power exploration studies in Sibuyan Island, supporting ongoing efforts to maximize solar energy utilization.

Streamflow prediction in ungauged watersheds remains a critical challenge in hydrological science due to the absence of in situ measurements, particularly in remote, data-scarce, and developing regions. This review synthesizes recent advancements in artificial intelligence (AI) for streamflow modeling, focusing on machine learning (ML), deep learning (DL), and hybrid modeling frameworks. Three core methodological domains are examined: regionalization techniques that transfer models from gauged to ungauged basins using physiographic similarity and transfer learning; synthetic data generation through proxy variables such as NDVI, soil moisture, and digital elevation models; and model performance evaluation using both deterministic and probabilistic metrics. Findings from recent literature consistently demonstrate that AI-based models, especially Long Short-Term Memory (LSTM) networks and hybrid attention-based architectures, outperform traditional conceptual and physically based models in capturing nonlinear hydrological responses across diverse climatic and physiographic settings. The integration of AI with remote sensing enhances generalizability, particularly in ungauged and human-impacted basins. This review also addresses several persistent research gaps, including inconsistencies in model evaluation protocols, limited transferability across heterogeneous regions, a lack of reproducibility and open-source tools, and insufficient integration of physical hydrological knowledge into AI models. To bridge these gaps, future research should prioritize the development of physics-informed AI frameworks, standardized benchmarking datasets, uncertainty quantification methods, and interpretable modeling tools to support robust, scalable, and operational streamflow forecasting in ungauged watersheds.

Flood triggered by heavy rains and typhoons leads to extensive damage to land and structures putting rural communities in crucial condition. Most of the studies on risk assessment focus on environmental factors, and building attributes have not been given attention. The five most expensive typhoon events in the Philippines were recorded in 2008–2013, causing USD 138 million in damage costs. This indicates the lack of tool/s that would aid in the creation of appropriate mitigation measure/s and/or program/s in the country to reduce damage caused by typhoons and flooding. Hence, this study highlights a structure vulnerability assessment approach employing the combination of analytical hierarchy process, physical structure attributes, and existing flood hazard maps by the local government unit. The available flood hazard maps were layered into base maps, and building attributes were digitized using a geographic information system. The result is an essential local scale risk map indicating the building risk index correlated to the structural information of each exposed structure. It was recorded that of 3094 structures in the community, 370 or 10.25% were found to be at moderate risk, 3094 (76.79%) were found to be high risk, and 503 (12.94%) were very high risk. The local government unit can utilize the resulting maps and information to determine flood risk priority areas to plan flood mitigation management strategies and educate people to improve the structural integrity of their houses. A risk map gives people an idea of what to improve in their houses to reduce their vulnerability to natural disasters. Moreover, the result of the study provides direction for future studies in the country to reduce loss and enhance structure resiliency against flooding.

Risk assessment is vital for humanities, especially in assessing natural and manmade hazards. Romblon, an archipelagic province in the Philippines, faces frequent typhoons and heavy rainfall, resulting in floods, with the Municipality of Santa Fe being particularly vulnerable to its severe damage. Thus, this research study intends to evaluate the flood risk of Santa Fe spatially using the fuzzy analytical hierarchy process (FAHP), taking into account data sourced from various government agencies and online databases. GIS was utilized to map flood-prone areas in the municipality. Hazard assessment factors included average annual rainfall, elevation, slope, soil type, and flood height. Distance to river, distance to road, types of building structure, mean age, gender ratio, and average annual income were considered parameters of vulnerability assessment. Exposure assessment considered land use, distance to evacuation facility, household number, and population density. Weights for each parameter were determined through pairwise comparison performed by experts. These weights were then incorporated into risk assessment estimation. The developed risk map identifies five high-risk barangays (small local government units). The study’s findings will enable local government units to establish flood mitigation programs, implement targeted mitigation measures, and formulate strategic response plans to lower risk and safeguard the residents of Santa Fe effectively.