Flood Modelling Research Articles

Identifying urban prone areas to flash floods: The case of Santa Cruz de Tenerife

Floods are the natural hazard that causes the largest annual losses in the world Urban expansion and population growth have made cities the most hazardous areas, mainly due to poor planning, occupation of the drainage network and soil sealing. Santa Cruz de Tenerife is one of the many cities worldwide threatened by this phenomenon. Its typically Mediterranean rainfall pattern, characterized by extreme precipitation events in short periods of time, together with its orography of steep ravines, short length and width, as well as its disorderly growth, make it a space prone to the occurrence of flash floods. In addition, the increase in torrential rainfall as a consequence of climate change and the tendency towards greater irregularity in precipitation is considerably intensifying the problem. This paper studies the characteristics of these episodes and the black spots inventoried in its General Management Plan (PGO for its initials in Spanish). On the other hand, flood modeling is carried out based on the rainfall characterization, whose maximum flows, in total, range between 500 and 1600 m3/s. Finally, a methodology that allows integrating both analyses to obtain a detailed hazard map is proposed as an alternative to the more traditional flood hazard analyses. A design storm of 288 mm is applied and the data is validated against the largest rainfall event on record, March 31, 2002. It has been shown that in an urban drainage network, the main watercourses and those that have disappeared due to urbanization represent areas susceptible to flooding and are the sectors that should be emphasized during the implementation of risk reduction measures. Finally, emphasis is placed on the need to integrate future climate projections of precipitation to better define the maximum flood flows.

Error correction method based on deep learning for improving the accuracy of conceptual rainfall-runoff model

Due to the complex runoff and concentration situation, flood forecasting for small and medium-sized catchments is very difficult. To improve the accuracy of flood forecasting, this study constructs a distributed model for flood forecasting based on the Xainanjiang (XAJ) model and the North China (NC) model respectively, and takes the deep learning model including LSTM and transformer to compare. Taking the Podi Basin and Shibazi Basin as study cases. LSTM, Transformer, and LSTPencoder models were used to correct the error of distributed models, and the differential evolution (DE) algorithm was used to optimize the model parameters. Taking the observed rainfall and distributed model results as input, the residuals of the simulation flow are fitted to improve the accuracy of the distributed model. The research results show that the NC model performs better than the XAJ, LSTM, and transformer models. Compared with the XAJ model, the average Nash-Sutcliffe coefficient of the NC model for the two catchments increased by 25.7 % and 5.87 % respectively. The performance of the NC+LSTPencoder model is better than other models. Compared with the NC model, the average Nash-Sutcliffe coefficient of the NC+LSTPencoder model for two catchments increased by 89.7 % and 1.12 % respectively, and the Root Mean Square Errors (RMSE) of the two catchments reduced by 79.1 % and 63.4 % respectively. The model proposed in this paper has strong correction ability, which has important significance for improving the accuracy of flood forecasts.

Advanced Method for Determining Land Plot’s Physical Surface

This study examines the issue of the accuracy of physical surface calculations for land plots with complex configurations and reliefs. The goal of the study was to develop a methodology for determining the surface area of land plots with complex configurations and reliefs. The presented model was based on the finite element method. The developed method allows one to evaluate a relief’s complexity by using a dimensionless mean physical surface complexity factor; a Fortran program was developed for the methodology. Experiments that proved the effectiveness of the methodology and a comparative analysis of those areas that were calculated by the presented method and TIN model were carried out. The research findings proved the practicability of the methodology for calculating the physical surfaces of land plots with complex configurations. The presented methodology can be used for flood modeling, landscape and vertical planning, etc.

Toward integrated dam assessment: evaluating multi-dimensional impacts of the Grand Ethiopian Renaissance Dam on Sudan

Abstract The Grand Ethiopian Renaissance Dam (GERD) on the Nile is expected to influence many ecosystem services, such as flood regulation, hydro-electricity production, food supply, and habitat provision, among others. Understanding these impacts (positive and negative) requires a comprehensive evaluation framework. This study develops and applies an integrated simulation framework for assessing the impacts of the GERD on Sudan, focusing on the simultaneous economywide effects of riverine flood hazards, irrigation water supply, hydropower generation, and floodplain-dependent industries, namely traditional fired clay brick production. The simulation framework incorporates three models: a river infrastructure system model, a flood model, and a Computable General Equilibrium Model. Results indicate positive impacts for hydropower generation and flood control, marginal benefits for water supply to existing irrigation, and negative consequences for brick production and the construction sector. Assuming that the GERD starts its long-term operation in 2025, we find an overall positive economic impact on Sudan’s Gross Domestic Product in 2025, with an increase of up to just over 0.1%, subject to river flow conditions. Recognizing the differences in impacts across sectors and income groups, the study emphasizes the need for interventions that ameliorate negative effects. While the study captures several impacts, other effects on the environment, recession agriculture, and soil fertility require further investigation. Still, our findings underscore the importance of adopting an integrated simulation approach to dam evaluation, acknowledging the interconnected nature of water and related sectors in national economies.

Clarifying urban flood response characteristics and improving interpretable flood prediction with sparse data considering the coupling effect of rainfall and drainage pipeline siltation

With climate warming and accelerated urbanisation, severe urban flooding has become a common problem worldwide. Frequent extreme rainfall events and the siltation of drainage pipes further increase the burden on urban drainage networks. However, existing studies have not fully considered the effects of rainfall and pipeline siltation on the response characteristics of flooding when constructing numerical models of urban flooding simulations. To solve this problem, a surface-subsurface coupling model was constructed by combining the Saint-Venant equation, Manning equation, a one-dimensional pipeline model (SWMM), and a two-dimensional surface overflow model (LISFLOOD-FP). Then, the SWMM model considering pipeline siltation and the two-dimensional surface overflow model (LISFLOOD-FP) were coupled with the flow exchange governing equation, and the urban flooding response characteristics considering the coupling effect of “rainfall and drainage pipeline siltation” were analysed. To enhance the solvability of waterlogging prediction, an intelligent prediction model of urban flooding based on Bayes-CNN-BLSTM was established by combining a convolutional neural network (CNN), bidirectional long short-term memory neural network (BLSTM), Bayesian optimisation (Bayes), and an interpretable loss function error correction method. The actual rainfall events and flooding processes recorded by the monitoring equipment at Huizhou University were used to calibrate and verify the model. The results show that in the Rainfall 1 and Rainfall 2 scenarios, the overload rates of the pipelines in the current siltation scenario were 60.06 % and 68.37 %, respectively, and the proportions of overflow nodes were 24.87 % and 25.89 %, respectively. When the drainage network was initially put into operation, the overload rates of the pipeline were 36.67 % and 41.16 %, and the overflow nodes accounted for 3.05 % and 4.06 %, respectively. The inundated area and volume of urban flooding increased when the combined siltation coefficient (CSC) was 0.2; therefore, two desilting schemes were determined. Under Rainfall 1, Rainfall 2, and the four rainfall recurrence periods, the Bayes-CNN-BLSTM model had clear advantages in terms of accuracy, reliability, and robustness.

A novel sensor preference method for proton exchange membrane fuel cell flooding fault diagnosis based on multi-algorithm

ABSTRACT During periods of high-power operation, proton exchange membrane fuel cell (PEMFC) produce water, which gradually accumulates at the cathode. It causes flooding faults and significantly impacts on PEMFC safety. The data collected by the sensors is a fundamental prerequisite for the flooding faults diagnosis in PEMFC. Consequently, it is critical to select sensors. However, the conventional methods for selecting sensors consider sensitivity and noise immunity, the number of sensors selected and the flood diagnostic performance are not optimized. To solve the above problems, this paper proposes a sensor preference method that combines the Mantel test and Spearman coefficient (MS method). This method first uses the Mantel test to analyze the correlation between two flooding evaluation indicators and the sensors, it identifies suitable sensors for diagnosing flooding faults. Subsequently, the Spearman coefficient eliminates redundant sensors. Additionally, a one-dimensional convolutional neural network is employed to construct a flooding diagnosis model. The MS method is contrasted with two traditional sensor selection methods. The results show that the MS method selected sensors yield superior model training and enhanced accuracy in diagnosing flooding, thereby ensuring PEMFC safety.

Does afforestation increase soil water buffering? A demonstrator study on soil moisture variability in the Alpine Geroldsbach catchment, Austria

This study employed an operational monitoring network to measure soil moisture and runoff behaviour continuously in the Alpine catchment Geroldsbach-Götzens, Austria. We hypothesize that afforestation can have a positive impact on soil water buffering. To analyse the impact of soil properties and vegetation cover changes on soil water dynamics, four experimental plots were established on grassland and monitoring stations were installed in the forest. The rainfall test site is equipped with an automatic weather station to obtain meteorological observations, and weirs to measure surface runoff of natural occurring precipitation events and artificial rainfall simulations. In the plots, 200 soil moisture sensors were installed at five different depths, aimed to track and visualize infiltration and subsurface flow processes. Another twenty sensors monitored soil moisture at different afforestation stages in the forested part of the catchment. The measurements show that soils covered with young and old-growth forest have a higher and more stable soil moisture content than grassland and soils with a lack of vegetation throughout the seasons. We observed large spatial differences at plot scale, where the spatial variability of soil moisture increases with depth and is highest during convective precipitation. The initial conditions and rainfall characteristics play an important role in infiltration processes and soil water storage. Our rainfall test site demonstrated the challenges of innovative monitoring techniques and that it offers opportunities for more experiments to gather evidence-based data as input for flood models. Overall findings confirm the sponge effect of forest soils and indicate that afforestation as Nature-Based Solution reduces the temporal soil moisture variability, buffering soil water during precipitation events, which can be beneficial for runoff reduction in Alpine catchments.

Enhancing Surface Water Monitoring through Multi-Satellite Data-Fusion of Landsat-8/9, Sentinel-2, and Sentinel-1 SAR

Long revisit intervals and cloud susceptibility have restricted the applicability of earth observation satellites in surface water studies. Integrating multiple satellites offers potential for more frequent observations, yet combining different satellite sources, particularly optical and SAR satellites, presents complexities. This research explores the data-fusion potential and limitations of Landsat-8/9 Operational Land Imager (OLI), Sentinel-2 Multispectral Instrument (MSI), and Sentinel-1 Synthetic Aperture (SAR) satellites to enhance surface water monitoring. By focusing on segmented surface water images, we demonstrate that combining optical and SAR data is generally effective and straightforward using a simple statistical thresholding algorithm. Kappa coefficients(κ) ranging from 0.80 to 0.95 indicate very strong harmony for integration across reservoirs, lakes, and river environments. In vegetative environments, integration with S1SAR shows weak harmony, with κ values ranging from 0.27 to 0.45, indicating the need for further studies. Global revisit interval maps reveal significant improvement in median revisit intervals from 15.87 to 22.81 days using L8/9 alone, to 4.51 to 7.77 days after incorporating S2, and further to 3.48 to 4.62 days after adding S1SAR. Even during wet season months, multi-satellite fusion maintained the median revisit intervals to less than a week. Maximizing all available open-source earth observation satellites is integral for advancing studies requiring more frequent surface water observations, such as flood, inundation, and hydrological modeling.

Armed conflict as a catalyst for increasing flood risk

Abstract Armed conflict has many adverse impacts beyond violence such as increasing risks of natural hazards. Analyses of the interactions between flood risks and armed conflict are essential for developing effective policies and strategies to address both challenges. This study aims to develop conceptual and analytical socio-hydrological frameworks for assessing how armed conflict can impact flood risks. The frameworks postulate a link between armed conflict and flood vulnerability, given that armed conflict creates unique challenges that exacerbate the effects of floods. Our conceptual framework identifies routes through which armed conflict affects vulnerability to floods, such as damage to infrastructure, population displacement and density, weak governance, and less awareness, resulting in lower resilience, higher susceptibility, and increased flood vulnerability and risk. Our analytical framework uses flood modeling to evaluate flood hazards and incorporates spatial data related to armed conflict zones, nighttime light, population classification by age, land price, land cover, and rural/urban areas classification. We take Khartoum, the capital city of Sudan, as a case study in view of its armed conflict that erupted in 2023. By highlighting the linkages between armed conflict and flood risk, this study contributes to conceptualizing the broader interlinkages between conflict and environmental systems. The study emphasizes the importance of integrating conflict analysis with disaster risk management strategies. We encourage collaboration between humanitarian, environmental, and security sectors to improve preparedness, response, and resilience in conflict-affected regions. While our analysis for Khartoum is based on conflict zones in the early stages of the conflict and uses simple estimates for conflict vulnerability contribution, the proposed frameworks provide groundwork for assessing changes in flood risk in Sudan and other conflict regions around the world.

Flood Modelling of Madi River Using HEC-RAS by Rain on Grid Approach

Indispensable for prognosticating flood impact in areas with limited data availability, reliable flood models are crucial for the analysis and mitigation of flood hazard. This study provides insight to accurately analyse flood scenarios by preparing a well calibrated 2D hydraulic model in HEC-RAS along with the Rain on Grid approach, which is subsequently used for hazard map preparation of Madi River. Hazard classification of flood depth indicated that for a 20-year return period, Moderate hazard levels covered 16.499%, High hazard levels covered 14.831%, and Very High hazard levels covered 68.670% of the total inundated area with reference to the depth hazard categories. Since, significant portion of the inundated area is classified as Very High Hazard; the finding of this research emphasizes the need of effective mitigation measure and provides essential insights crucial for flood risk assessment.

A tight coupling model for urban flood simulation based on SWMM and TELEMAC-2D and the uncertainty analysis

The urban flood of rainstorm has posed a major threat to human life and property in recent years, seriously affecting the sustainable development of society. The numerical model can simulate how an urban flood develops and moves, and then guide how to reduce the disaster's impact. This study develops a tight coupling model named STUFMS based on Storm Water Management Model (SWMM) and TELEMAC-2D for urban flood simulation. Theoretical and practical cases were respectively applied to verify the reasonability and accuracy of the model. The theoretical case demonstrates that the STUFMS can better simulate the process of water exchange between the surface and rainwater drainage systems while the practical case suggests that the change in water level and the flooded area simulated by the STUFMS are basically consistent with the typical historical rainfall events. The uncertainty analysis revealed that terrain resolution and temporal resolution of rainfall series have a significant impact on the inundation scopes. Generally, the STUFMS model behaved well in simulating the urban flood process, offering a novel tool for numerical modeling of urban flood.

Adjoint-based sensitivity analysis and assimilation of multi-source data for the inference of spatio-temporal parameters in a 2D urban flood hydraulic model

This contribution presents a novel approach for the calibration of distributed parameters in a 2D urban flood hydraulic model. It focuses on the challenging issue of inferring distributed friction parameters from multi-source heterogeneous spatio-temporal observations of their hydraulic signatures in the context of an urban flash flood in a complex street network. A variational data assimilation algorithm is used to infer high-dimensional multi-variate parameters (spatialized friction and inflow discharge time series) using multi-source observations. This method relies on a differentiable 2D shallow water hydraulic model which enables to generate high-resolution sensitivity maps of local gradients and Derivative-based Global Sensitivity Measures (DGSM), enabling to guide adequate definition of parameter spatialization for the data assimilation process. Assimilated data include real local limnigraphic measurements and high-water marks collected after a major flood event, as well as modeled flow velocity used in twin experiments setups. This study is the first to leverage high-water marks with a variational method for the calibration of distributed parameters in an urban flood model. The multi-source data is used to infer inflow hydrographs and distributed friction parameters in setups of varying complexity. In the main setup, the complex structure of the street network, along with the sensitivity maps and hydraulics expertise led to define a model configuration with 45 friction patches. A high-dimensional parameter vector composed of these friction values and an upstream inflow is inferred simultaneously by assimilating real limnigraphic data and high-water marks. This leads to an increase in model fit to observations and satisfying parameter estimates.

Urban flash flood hazard mapping using machine learning, Bahir Dar, Ethiopia

ABSTRACT Increased frequency and magnitude of flooding pose a significant natural hazard to urban areas worldwide. Mapping flood hazard areas are crucial for mitigating potential damage to human life and property. However, conventional hydrodynamic approaches are hindered by their extensive data requirements and computational expenses. As an alternative solution, this paper explores the use of machine learning (ML) techniques to map flood hazards based on readily available geo-environmental variables. We employed various ML classifiers, including decision tree (DT), random forest (RF), XGBoost (XGB), and k-nearest neighbor (kNN), to assess their performance in flood hazard mapping. Model evaluation was conducted using the area under the receiver operating characteristic curve (AUC) and root mean square error (RMSE). Our results demonstrated promising outcomes, with AUC values of 93% (DT), 97% (RF), 98% (XGB), and 91% (kNN) for the validation dataset. RF and XGB have slightly higher performance than DT and kNN and distance to river was the most important factor. The study highlights the potential of ML for urban flood modeling, offering reasonable accuracy and supporting early warning systems. By leveraging available geo-environmental variables, ML techniques provide valuable insights into flood hazard mapping, aiding in effective urban planning and disaster management strategies.

Physics-informed geostatistical approach (PIGA) for real-time fluvial flood modeling

This study presents the Physics-Informed Geostatistical Approach (PIGA), a novel methodology aimed at improving flood prediction accuracy in riverine systems during hurricane events. PIGA integrates reduced spatial correlations derived from fluvial hydrodynamic models with a reduced geostatistical approach (RGA) based on monitoring data to provide real-time estimations of water surface elevations (WSE) across river channels and reaches. Focusing on the Savannah River basin, an area prone to riverine flooding during hurricane seasons, we developed a 1D-2D HEC-RAS model as the physical model and compared its performance with PIGA for various hurricane events, including Hurricane Matthew, Irma, Dorian, and Idalia. Our findings reveal that PIGA consistently outperforms the HEC-RAS model in predicting WSE, particularly in areas with limited bathymetry data. Statistical analyses demonstrate significant improvements in prediction accuracy achieved by PIGA, emphasizing its potential as a reliable tool for flood prediction in data-deficient regions. Additionally, we explore the transferability of reduced spatial correlations across different hurricane events. Our results indicate that spatial correlations derived from one hurricane event can effectively predict WSE for other events, with Hurricane Irma’s spatial correlations proving to be the most versatile for our study site. However, we also observe variability in spatial correlations among different hurricane events, highlighting the importance of selecting the optimal alternative spatial reference for prediction. Furthermore, we highlight PIGA’s computational efficiency, with simulations completed in significantly less time compared to traditional physical models, rendering its potential to provide real-time prediction of WSE during flooding events.

Elevating Pakistan’s flood preparedness: a fuzzy multi-criteria decision making approach

In South Asia, Pakistan has a long and deadly history of floods that cause losses to various infrastructures, lives, and industries. This study aims to identify the most appropriate flood risk mitigation strategies that the government of Pakistan should adopt. The assessment of flood risk mitigation strategies in this study is based on certain criteria, which are analyzed using the fuzzy full consistency method. Moreover, flood risk mitigation strategies are evaluated by using the fuzzy weighted aggregated sum product assessment (WASPAS) method, considering previously prioritized criteria. According to the results, lack of governance, lack of funding and resources, and lack of flood control infrastructure are the most significant flood intensifying factors and act as major criteria for assessing flood risk mitigation strategies in Pakistan. Adopting hard engineering strategies (e.g., dams, reservoirs, river straightening and dredging, embankments, and flood relief channels), maintaining existing infrastructure, and adopting soft engineering strategies (flood plain zoning, comprehensive flood risk assessment, and sophisticated flood modeling) are identified as the top three flood risk mitigation strategies by the fuzzy WASPAS method. The highest weight (0.98) was assigned to the adoption of hard engineering strategies to mitigate flood risks. The study introduces a novel dimension by analyzing the real-time impact of the unprecedented 2022 floods, during which approximately one-third of the nation was submerged. This focus on a recent and highly significant event enhances the study’s relevance and contributes a unique perspective to the existing literature on flood risk management. The study recommends that the government of Pakistan should prioritize hard engineering strategies for effective flood risk mitigation. It also recommends that the government should incorporate these strategies in the national policy framework to reduce flood losses in the future.

A hybrid surrogate model for real-time coastal urban flood prediction: An application to Macao

Tropical cyclones could cause co-occurrences of storm tides and rainfall and, therefore, induce flooding hazards, posing high risks to coastal cities. Accurate and timely prediction of flood hazards in time–space domain is essential for flood risk management. In this study, a hybrid surrogate model is proposed for real-time flooding prediction by considering the compound effects of storm tides, rainfall, and drainage outflows. The hybrid surrogate model combines a long short-term memory (LSTM) neural network for predicting drainage outflows with a one-dimensional convolutional neural network (1D CNN) for predicting water depths. The model is tested using performance metrics, and the simulation results agree well with the historical measurements. Moreover, a sensitivity analysis of the drainage outflows using the modified Morris screening method reveals the importance of considering drainage systems in flood modelling, particularly when rainfall return periods are relatively small. The sensitivity indices vary over the computation domain in terms of different driving factors, with positive values corresponding to rainfall-dominated area while negative values corresponding to storm tide-dominated area. The computation cost of the model is quite low, and the fast prediction speed could provide a sound basis for early warning and real-time flood management. The proposed hybrid surrogate model offers a promising function for rapid and accurate flood inundation prediction in coastal cities, enabling more effective flood risk management and emergency response planning.

Using social cartographies for the calibration of two-dimensional hydraulic flood models

Using social cartographies for the calibration of two-dimensional hydraulic flood models

Urban flooding simulation and flood risk assessment based on the InfoWorks ICM model: A case study of the urban inland rivers in Zhengzhou, China.

Urban flooding intensifies with escalating urbanization. This study focuses on Xiong'er river as the study area and couples a 1D/2D urban flooding model using InfoWorks ICM (Integrated Catchment Modeling). Ten scenarios are set respectively with a rainfall return period of 5a 10a, 20a, 50a, and 100a, alongside rainfall durations of 1 and 24 h. Subsequently, the H-V (hazard-vulnerability) method was applied to evaluate urban flooding risk. Three indicators were selected for each of hazard factors and vulnerability factors. The relative weight values of each indicator factor were calculated using the AHP method. The result shows that (1) flood depth, rate, and duration escalate with longer rainfall return periods, yet decrease as the duration of rainfall increases; (2) as the rainfall return period lengthens, the proportion of node overflow rises, whereas it diminishes with longer rainfall durations, leading to an overall overloaded state in the pipeline network; and (3) the distribution in the research area is mainly low-risk areas, with very few extremely high-risk. Medium to high-risk areas are mainly distributed on both sides of the river, in densely built and low-lying urban areas. This study demonstrates that the model can accurately simulate urban flooding and provide insights for flood analyses in comparable regions.

Zoning and regulation of compound flooding in coastal cities coupled with tracer method

Urban inland rivers play a significant role in mitigating flooding. However, the influence of their discharge on urban flooding affected by different flood drivers remains to be fully explored. Taking a catchment area in Haikou City, Hainan Province, China as an example, in light of the urban flooding model coupled with the water tracer method, this study investigates the degree of inundation in each flood zone under different inland river flows. The flood zones are determined by the flooding simulation results of three cases, and then are verified by the zonation based on the tide tracer approach. Finally, the tracer method is used to study the impact of urban inland rivers on flooding and the connection of hydraulic and water volume between rivers and pipelines. The results indicate that the inundation area decreased by 3.71 % as the river flow increased from 15 to 25 m3/s. In the process of river flow rising from 5 to 45 m3/s, The average flooding depth in the rainfall-affected area climbs slowly from 0.53 m to 0.62 m; In the tidal-affected area, the average flooding depth drops from 0.52 m to 0.12 m when the inland river flow increases from 5 to 25 m3/s, and rises from 0.12 m to 0.54 m when the inland river flow continues from 25 to 45 m3/s; The percentage of pipelines grows from 18.5 % to 28.0 %. This study provides valuable scientific insights and support for flood prevention planning and flood control strategies in coastal cities.

Assessment of CO2 Sequestration Capacity in a Low-Permeability Oil Reservoir Using Machine Learning Methods

The CO2 sequestration capacity evaluation of reservoirs is a critical procedure for carbon capture, utilization, and storage (CCUS) techniques. However, calculating the sequestration amount for CO2 flooding in low-permeability reservoirs is challenging. Herein, a method combining numerical simulation technology with artificial intelligence is proposed. Based on the typical geological and fluid characteristics of low-permeability oil reservoirs in the Liaohe oilfield, the CMG 2020 version software GEM module is used to establish a model for CO2 flooding and sequestration. Meanwhile, a calculation method for the effective sequestration coefficient of CO2 is established. We systematically study the sequestration rules in low-permeability reservoirs under varying conditions of permeability, reservoir temperature, and initial reservoir pressure. The results indicate that, as the permeability and sequestration pressure of the reservoir increase, oil recovery gradually increases. The proportion of structurally bound sequestration volume increases from 55% to 60%. Reservoir temperature has minimal impact on both the recovery rate and the improvement in sequestration efficiency. Sequestration pressure primarily improves sequestration efficiency by increasing the dissolution of CO2 in the remaining oil and water. The calculation chart for the effective sequestration coefficient, developed using artificial intelligence algorithms under multi-factor conditions, enables accurate and rapid evaluation of the sequestration potential and the identification of favorable sequestration areas in low-permeability reservoirs. This approach provides valuable technical support for CO2 flooding and sequestration in pilot applications.