Forecasting Challenge Research Articles

Impact of the Upper-Tropospheric Cold Low on the Genesis of Typhoon Hagupit (2020)

Abstract Typhoon Hagupit (2020), which formed unexpectedly close to land, posed great challenges for forecasters. During its genesis, there was a westward-moving upper-tropospheric cold low (UTCL) to its north. This study investigated the impact of this UTCL on the genesis process using numerical simulations. In the semi-idealized experiment with this UTCL removed (run-Rcold), pre-Hagupit develops faster, but its track drifts southward in the later stage compared with the control experiment (run-cnl). In the experiment with enhanced UTCL (run-Ecold), the simulated track is similar to that in run-cnl, but pre-Hagupit does not develop into a tropical storm. In run-cnl and run-Ecold, the environmental vertical wind shear is larger than that in run-Rcold in the first 2 days, and the simulated pre-Hagupit experiences two prominent dry-air intrusions in the middle and upper troposphere. At the second intrusion, when the weakened UTCL has moved within 2° of pre-Hagupit, the convection in both experiments decays significantly, and the development of the midlevel vortex begins to lag behind that in run-Rcold, and so does the vertical alignment of the low- and midlevel vortices. The UTCL influences the movement of pre-Hagupit by modifying the large-scale steering flows, especially those above 600 hPa. In run-Rcold, due to the absence of the northward component of wind fields related to the UTCL circulation, pre-Hagupit starts to move west-northwestward instead of northwestward as in run-cnl and run-Ecold. Significance Statement Typhoon Hagupit (2020) got named near the 24-h warning line of China. TCs crossing this line are considered to have a significant impact on China within 24 h, or may make landfall within 24 h. After formation, Hagupit rapidly intensified to its peak intensity of 42 m s−1 in 48 h, and made landfall in Zhejiang Province at severe typhoon strength after another 8 h. Both the unexpected genesis and the rapid intensification of Hagupit posed great challenges for forecasters and deserve further investigation. This study focused on the genesis process. We noticed that there was a westward-moving upper-tropospheric cold low (UTCL) in the north during the formation of Hagupit. We have conducted three numerical experiments to investigate the impact of this UTCL on the genesis of Hagupit, and found that the UTCL is an important factor affecting the genesis process. It is detrimental to the vortex development. If the UTCL is removed, Hagupit will develop into a tropical storm more quickly, but its potential landfall point of Hagupit will shift from the southeast coast of China to the Philippines.

Medium-term water consumption forecasting based on deep neural networks

Water consumption forecasting is an essential tool for water management, as it allows for efficient planning and allocation of water resources, an undervalued but indispensable resource for all living beings. With the increasing demand for accurate and timely water forecasting, traditional forecasting methods are proving to be insufficient. Deep learning techniques, which have shown remarkable performance in a wide range of applications, offer a promising approach to address the challenges of water consumption forecasting. In this work, the use of deep learning models for medium-term water consumption forecasting of residential areas is explored. A deep feed-forward neural network is developed to predict water consumption of a company’s customers for the next quarter. First, customers are grouped according to their consumption as these customers include both household consumers and special consumers such as public swimming pools, sports halls or small industries. Then, a deep feed-forward neural network is designed for household customers by obtaining the optimal values for those hyperparameters that have a great influence on the network performance. Results are reported using a real-world dataset composed of the water consumption from 1999 to 2015 on a quarterly basis, corresponding to 3262 clients of a water supply company. Finally, the proposed algorithm is evaluated by comparing it with other reference algorithms including an LSTM network.

Research on the short-term wind power prediction with dual branch multi-source fusion strategy

The smooth operation of the power system imposes high requirements on wind power forecasting. Given the forecasting challenges brought by the coexistence of strong and weak disturbances in wind power data, this paper proposes a hierarchical anti-disturbance mechanism to raise the accuracy of single-point wind power prediction. In the first-level disturbance processing, we prioritize the treatment of strong disturbances in wind power data through a dual-branch multi-source fusion prediction structure. The wind power subsequences with distinct time–frequency characteristics are divided into two sets, processed by the stationary set prediction branch and the drastic set prediction branch, respectively. For the drastic set, we incorporate microenvironmental multi-source data surrounding the wind turbine as input and propose a parallel-structured attention fusion module CA (Convolution attention fusion block) to provide effective data support for the prediction module, then extract rich fusion features through deep temporal LSTM algorithm and ultimately achieve fine-grained forecasting. For weak disturbances that have not been adequately addressed in the previous step, we conduct a secondary treatment through error correction strategy. By employing the hierarchical processing approach, this paper accomplishes a comprehensive handling of disturbances with different intensities. Experimental results on four data sets show that the proposed model DEWFM (Dual-branch and error correction wind power forecast) demonstrates remarkable performance advantages in comparing with the baseline model and other advanced models, the average values of MAE reaching 1.679, revealing the effectiveness of the proposed method in enhancing the precision of short-term wind power prediction.

Towards Efficient Battery Electric Bus Operations: A Novel Energy Forecasting Framework

As the adoption of battery electric buses (BEBs) in public transportation systems grows, the need for precise energy consumption forecasting becomes increasingly important. Accurate predictions are essential for optimizing routes, charging schedules, and ensuring adequate operational range. This paper introduces an innovative forecasting methodology that combines a propulsion and auxiliary energy model with a novel concept, the environment generator. This approach addresses the primary challenge in electric bus energy forecasting: estimating future environmental conditions, such as weather, passenger load, and traffic patterns, which significantly impact energy demand. The environment generator plays a crucial role by providing the energy models with realistic input data. This study validates various models with different levels of model complexity against real-world operational data from a case study of over one year with 16 electric buses in Göttingen, Germany. Our analysis thoroughly examines influencing factors on energy consumption, like altitude, temperature, passenger load, and driving patterns. In order to comprehensively understand energy demands under varying operational conditions, the methodology integrates data-driven models and physical simulations into a modular and highly accurate energy predictor. The results demonstrate the effectiveness of our approach in providing more accurate energy consumption forecasts, which is essential for efficient electric bus fleet management. This research contributes to the growing body of knowledge in electric vehicle energy prediction and offers practical insights for transit authorities and operators in optimizing electric bus operations.

Forecasting air passenger traffic and market share using deep neural networks with multiple inputs and outputs.

In this study, we address the challenge of accurate time series forecasting of air passenger demand using historical market demand data from the U.S. commercial aviation industry in the 21st century. Commercial aviation is a major contributor to the U.S. economy, directly or indirectly generating ~US$1.37 trillion annually, or 5% of annual GDP, and supporting more than 10 million jobs (Airlines for America, 2024). Over 1 billion passengers flew through U.S. airports in 2023 (Bureau of Transportation Statistics, 2024a). Using multiple correlated time series inputs predicts future values of multiple interrelated time series and leverages their mutual dependencies to enhance accuracy. In this study, we introduce a two-stage algorithm employing a deep neural network for correlated time series forecasting, addressing scenarios where multiple input variables are interrelated. This approach is designed to capture the influence that one time series can exert on another, thereby enhancing prediction accuracy by leveraging these interdependencies. In the first stage, we fit four Recurrent Neural Network (RNN) models to generate accurate univariate forecasts, each functioning as a single input-output model to predict aggregated market demand. The Gated Recurrent Unit (GRU) model was the top performer for our dataset overall. In the second stage, we apply the best fitted model (GRU Model) from Stage 1 to each individual competitor (disaggregated from the market) and then merge all input tensors using the Concatenate function. We hope to contribute to the relevant body of knowledge with a deep neural network framework for forecasting market share among competitors in the U.S. commercial aviation industry, as no similar approach has been documented in the literature. Given the importance of the industry, there is potentially great value in applying sophisticated forecasting techniques to achieve accurate predictions of air passenger demand. Moreover, these techniques may have wider applications and can potentially be employed in other contexts.

Going green with artificial intelligence: The path of technological change towards the renewable energy transition

Research background: The twin pressures of economic downturn and climate change faced by countries around the world have become more pronounced over the past decade. A renewable energy transition is believed to play a central role in mitigating the economic-climate paradox. While the architectural and computational power of artificial intelligence is particularly well suited to address the challenges of massive data processing and demand forecasting during a renewable energy transition, there is very scant empirical assessment that takes a social science perspective and explores the effects of AI development on the energy transition. Purpose of the article: This paper aims to answer two key questions: One is, how does AI software development promote or inhibit the shift of energy consumption towards renewables? The other is, under what policy interventions does AI software development have a more positive effect on promoting renewable energy consumption? Methods: We employ a dataset of 62 economies covering the period 2011–2020 to analyze the impact of AI software development on the energy transition, where possible confounders, including political and economic characteristics and time-invariant elements, are controlled using fixed-effects estimation along with specified covariates. Findings & value added: AI software development can promote the energy transition towards renewables. There is suggestive evidence that the core mechanism linking such a positive relationship tends to lie in improving innovation performance in environmental monitoring rather than in green computing. Government support for R&D in renewable energy technologies is found to be significantly beneficial for harnessing the positive impact of AI software development on the energy transition. Compared to non-market-based environmental policies, market-based environmental policies have a more significant positive moderating effect on the relationship between AI software development and energy transition.

Powerformer: A temporal-based transformer model for wind power forecasting

Wind Power Forecasting has emerged as a critical and dynamic research area in response to the growing demand for renewable energy. The unpredictable and stochastic nature of wind conditions, encompassing factors such as wind speed, wind direction, air temperature, and barometric pressure, poses unique challenges for accurate forecasting of wind power generation. Reliable wind power generation forecasts are essential for optimizing energy grid management, ensuring grid stability, and facilitating the integration of wind energy with existing power systems. To address these challenges, this research introduces Powerformer, a Transformer-based model designed to improve the accuracy of wind power prediction. Powerformer utilizes the infrastructure of the Transformer with innovative modifications to address the complexity of wind power prediction, enhancing temporal feature extraction capabilities while reducing complexity. The research in this study includes a comprehensive set of experiments, revealing that Powerformer achieves superior results among all models. Furthermore, the model exhibits stronger robustness, as confirmed through a series of ablation experiments validating the reasonableness of the model design.

Alleviating distribution shift and mining hidden temporal variations for ultra-short-term wind power forecasting

Randomness and non-stationarity are common challenges in wind power forecasting (WPF). Many studies focus on randomness but usually ignore the non-stationarity which leads to distribution shift and affects prediction accuracy. To address the distribution shift problem, an alleviating distribution shift using the recent difference characterization (Dish-RDC) method is proposed as a general neural paradigm for WPF. Dish-RDC categorizes the distribution shift into intra-space and inter-space shifts. By employing the RDC, the method facilitates the mapping of input sequences to learnable distribution coefficients that better estimate the distribution. Furthermore, real-world time series often exhibit multi-periodicity, yet existing models face limitations in capturing this temporal variation. To address this issue, our research introduces the Temporal 2D-Variation Model (TimesNet) in WPF. This innovative model extends time variation analysis into a 2D space based on multi-periodicity. By using 2D kernels to model these variations, TimesNet can effectively incorporate advanced computer vision techniques into WPF. Combining these approaches, we developed Dish-RDC-TimesNet, a hybrid model. Experiments show it reduced mean absolute error (MAE) by 47.10 % and 20.63 % on two datasets compared to benchmark models. Moreover, integrating Dish-RDC with benchmark models decreased MAE by 39.79 % and 17.85 % on these datasets.

An Improved Hybrid Approach for Daily Electricity Peak Demand Forecasting during Disrupted Situations: A Case Study of COVID-19 Impact in Thailand

Accurate electricity demand forecasting is essential for global energy security, reducing costs, ensuring grid stability, and informing decision making in the energy sector. Disruptions often lead to unpredictable demand shifts, posing greater challenges for short-term load forecasting. Understanding electricity demand patterns during a pandemic offers insights into handling future disruptions. This study aims to develop an effective forecasting model for daily electricity peak demand, which is crucial for managing potential disruptions. This paper proposed a hybrid approach to address scenarios involving both government intervention and non-intervention, utilizing integration methods such as stepwise regression, similar day selection-based day type criterion, variational mode decomposition, empirical mode decomposition, fast Fourier transform, and neural networks with grid search optimization for the problem. The electricity peak load data in Thailand during the year of the COVID-19 situation is used as a case study to demonstrate the effectiveness of the approach. To enhance the flexibility and adaptability of the approach, the new criterion of separating datasets and the new criterion of similar day selection are proposed to perform one-day-ahead forecasting with rolling datasets. Computational analysis confirms the method’s effectiveness, adaptability, reduced input, and computational efficiency, rendering it a practical choice for daily electricity peak demand forecasting, especially in disrupted situations.

Fog Water: A General Review of Its Physical and Chemical Aspects

Studies concerning fog water have been rapidly increasing due to its negative impacts on different environmental processes. However, fog water harvesting has become beneficial in various countries to overcome water scarcity. Accurate fog forecasting remains a challenging issue due to its spatio-temporal variability and uncertainties despite the development and efforts made to understand its chemistry and microphysics. The literature proved that the decrease in fog frequency over time in most countries is mainly attributed to the improvement in air quality or the change in regional climatic conditions. The current fog review summarizes its different types and collectors, life cycle, and impacts, the effects of aerosols, and the latest results concerning its forecast challenges and frequency. It also highlights the major chemical processes along with the main field studies performed on fog water. The aim of this work is not to provide a criticism about fog but to present a general comprehensive review of its physical and chemical aspects covering up to 330 research and review papers aimed to serve as a basis for new challenges and findings about fog water.

Enhancing Short-Term Electrical Load Forecasting for Sustainable Energy Management in Low-Carbon Buildings

Accurate short-term forecasting of electrical energy loads is essential for optimizing energy management in low-carbon buildings. This research presents an innovative two-stage model designed to address the unique challenges of Electricity Load Forecasting (ELF). In the first phase, robust data preprocessing techniques are employed to handle issues such as outliers, missing values, and data normalization, which are common in electricity consumption datasets in the context of low-carbon buildings. This data preprocessing enhances data quality and reliability, laying the foundation for accurate modeling. Subsequently, an advanced data-driven modeling approach is introduced. The model combines a novel residual Convolutional Neural Network (CNN) with a layered Echo State Network (ESN) to capture both spatial and temporal dependencies in the data. This innovative modeling approach improves forecasting accuracy and is tailored to the specific complexities of electrical power systems within low-carbon buildings. The model performance is rigorously evaluated using datasets from low-carbon buildings, including the Individual-Household-Electric-Power-Consumption (IHEPC) dataset from residential houses in Sceaux, Paris, and the Pennsylvania–New Jersey–Maryland (PJM) dataset. Beyond traditional benchmarks, our model undergoes comprehensive testing on data originating from ten diverse regions within the PJM dataset. The results demonstrate a significant reduction in forecasting error compared to existing state-of-the-art models. This research’s primary achievement lies in its ability to offer an efficient and adaptable solution tailored to real-world electrical power systems in low-carbon buildings, thus significantly contributing to the broader framework of modeling, simulation, and analysis within the field.

Recent advances in operational tropical cyclone genesis forecast

Tropical cyclone (TC) genesis prediction is a major scientific challenge to the TC operation and research community. This report surveys the current status of TC genesis forecasts by a number of major operational centers covering the key ocean basins across both hemispheres. Since IWTC-9, we see an emergence of probabilistic TC genesis forecast products by operational centers, typically supported by the statistical processing of a combination of ensemble prediction and satellite analysis, covering time periods of couple of days to weeks ahead. The prevalence of multi-center grand ensemble approach highlights the uncertainties involved and the forecast challenges in quantitative genesis prediction. While operational practice might differ across agencies, verification efforts generally report a steady or slightly improving skill level in terms of reliability, which likely results from the continual improvement in global numerical weather prediction capability.

Ultra-short-term forecasting of agricultural intelligent greenhouse power load based on ISDS and MDUS-LSTM

The agricultural smart greenhouse electric load differs significantly from the traditional building electric load. It is more susceptible to the influence of meteorological conditions, featuring poor regularity and significant random fluctuations, so load forecasting faces new challenges. To address this challenge, this paper focuses on a variety of meteorological and historical similar feature extraction, innovates model updating strategies, and proposes a new ultra-short-term forecasting method for agricultural smart greenhouse electric loads. Firstly, an improved similar day selection (ISDS) method is designed. This method considers both trend similarity and magnitude similarity of time series. It sets weights according to the degree of influence of different meteorological features on load, thus improving the learning efficiency of the model. Next, a model dynamic update strategy (MDUS) is designed. This strategy consists of initial training of forecasting model parameters based on historical similar daily loads and online updating of forecasting model parameters based on adjacent daily load data. Then, the forecasting model is trained online and fine-tuned with the parameters based on the adjacent daily load data. The dynamically updated forecasting model is used to achieve ultra-short-term forecasting of the electric load to improve the forecasting accuracy and adaptability of the model. Finally, the effectiveness of the proposed method is verified by actual electrical load data, real-time meteorological data, and NWP data collected in an agricultural smart greenhouse in Shouguang, China.

The future of military medical evacuation: literature analysis focused on the potential adoption of emerging technologies and advanced decision-analysis techniques

A fundamental component of any military medical support system is medical evacuation. The main goal of evacuation is to reduce mortality among critically injured combat casualties. To achieve this goal, several decision problems including, the location of medical treatment facilities, relocation, dispatching, and routing have to be effective across all levels (tactical, operational, and strategic). This study concentrates on the three key types of medical evacuation (MEDEVAC) systems—forward, tactical, and strategic—and the related decision problems. Even though, over the last few years, some review papers have discussed the different topics of MEDEVAC systems (e.g., the evolution of MEDEVAC, evacuation timelines, and types of injuries), no research has been conducted on the full range (i.e., total care pathway) of MEDEVAC systems and the adoption of emerging technologies to improve future MEDEVAC. In this paper, a systematic review of the literature is described, including the decision problems involved in the total military medical evacuation process. This paper also reviews forecast challenges of future MEDEVAC and potential emerging technologies, concepts, and advanced decision-analysis methods to tackle these challenges. In future MEDEVAC processes, emerging technologies and concepts will be important to support improved medical capability; however, military planners will also need to adopt advanced decision-support techniques to efficiently employ these technologies.

Attractor Inspired Deep Learning for Modelling Chaotic Systems

Predicting and understanding the behavior of dynamic systems have driven advancements in various approaches, including physics-based models and data-driven techniques like deep neural networks. Chaotic systems, with their stochastic nature and unpredictable behavior, pose challenges for accurate modeling and forecasting, especially during extreme events. In this paper, we propose a novel deep learning framework called Attractor-Inspired Deep Learning (AiDL), which seamlessly integrates actual statistics and mathematical models of system kinetics. AiDL combines the strengths of physics-informed machine learning and data-driven methods, offering a promising solution for modeling nonlinear systems. By leveraging the intricate dynamics of attractors, AiDL bridges the gap between physics-based models and deep neural networks. We demonstrate the effectiveness of AiDL using real-world data from various domains, including catastrophic weather mechanics, El Niño cycles, and disease transmission. Our empirical results showcase AiDL’s ability to substantially enhance the modeling of extreme events. The proposed AiDL paradigm holds promise for advancing research in Time Series Prediction of Extreme Events and has applications in real-world chaotic system transformations.

Deep learning integration optimization of electric energy load forecasting and market price based on the ANN–LSTM–transformer method

Introduction: Power load forecasting and market price analysis have become crucial in the context of complex power energy systems and volatile market prices. Deep learning technology has gained significant attention in time series forecasting, and this article aims to enhance the accuracy and reliability of power load and market price predictions by integrating and optimizing deep learning models.Methods: We propose a deep learning framework that combines artificial neural networks (ANNs), long short-term memory (LSTM), and transformer models to address key challenges in electricity load forecasting and market price prediction. We leverage ANNs for their versatility and use LSTM networks for sequence modeling to generate initial predictions. Additionally, we introduce transformer technology and utilize its self-attention mechanism to capture long-distance dependencies within the data, further enhancing the model’s performance.Results: In our experiments, we validate the proposed framework using multiple public datasets. We compare our method with traditional forecasting approaches and a single-model approach. The results demonstrate that our approach outperforms other methods in predicting power load and market prices. This increased accuracy and reliability in forecasting can be of significant value to decision-makers in the energy sector.Discussion: The integration of deep learning models, including ANN, LSTM, and transformer, offers a powerful solution for addressing the challenges in power load and market price prediction. The ability to capture long-distance dependencies using the transformer's self-attention mechanism improves forecasting accuracy. This research contributes to the field of energy and finance by providing a more reliable framework for decision-makers to make informed choices in a complex and dynamic environment.

A novel kernel ridge grey system model with generalized Morlet wavelet and its application in forecasting natural gas production and consumption

Natural gas production (NGP) and consumption (NGC) always exhibit high nonlinearity, posing challenges for accurate small-sample forecasting. In this work, a novel kernel ridge grey system model with an extended parametric Morlet wavelet (GMW-KRGM) is proposed by integrating the kernel ridge regularization and grey system modelling within a partially linear regression framework and trained by the conjugate gradient method to mitigate the ill-posed problem. Besides, a weighted multi-objective optimization strategy is designed for model hyperparameter optimization and solved by the grey wolf optimizer (GWO). Six real-world NGP and NGC forecasting cases are carried out and empirical results demonstrate that the proposed GMW-KRGM model with optimal hyperparameters solved by GWO always yields superior forecasting performance than the other 2 machine learning models and 7 conventional grey system benchmarks with out-of-sample mean average percentage error (MAPE) improved in 7.4245%–91.8392% and 14.7303%–42.67% on average, respectively and yields more precise forecasting accuracy with fast and stable convergence than the other 5 optimization algorithms with improved MAPE range from 9.5608% to 48.2584%, indicating that the proposed model holds the capability to effectively deal with the nonlinear complex system and has great potential in nonlinear small sample forecasting.

Prediction of natural dry-snow avalanche activity using physics-based snowpack simulations

Abstract. Predicting the timing and size of natural snow avalanches is crucial for local and regional decision makers but remains one of the major challenges in avalanche forecasting. So far, forecasts are generally made by human experts interpreting a variety of data and drawing on their knowledge and experience. Using avalanche data from the Swiss Alps and one-dimensional physics-based snowpack simulations for virtual slopes, we developed a model predicting the probability of dry-snow avalanches occurring in the region surrounding automated weather stations based on the output of a recently developed instability model. This new avalanche day predictor was compared with benchmark models related to the amount of new snow. Evaluation on an independent data set demonstrated the importance of snow stratigraphy for natural avalanche release, as the avalanche day predictor outperformed the benchmark model based on the 3 d sum of new snow height (F1 scores: 0.71 and 0.65, respectively). The averaged predictions of both models resulted in the best performance (F1 score: 0.75). In a second step, we derived functions describing the probability for certain avalanche size classes. Using the 24 h new snow height as proxy of avalanche failure depth yielded the best estimator of typical (median) observed avalanche size, while the depth of the deepest weak layer, detected using the instability model, provided the better indicator regarding the largest observed avalanche size. Validation of the avalanche size estimator on an independent data set of avalanche observations confirmed these findings. Furthermore, comparing the predictions of the avalanche day predictors and avalanche size estimators with a 21-year data set of re-analysed regional avalanche danger levels showed increasing probabilities for natural avalanches and increasing avalanche size with increasing danger level. We conclude that these models may be valuable tools to support forecasting the occurrence of natural dry-snow avalanches.

ADCT-Net: Adaptive traffic forecasting neural network via dual-graphic cross-fused transformer

The rapid development of road traffic networks has provided a wealth of research data for intelligent transportation systems. We are faced with vast high-dimensional traffic flow data, characterized by complex spatio-temporal dependencies, waiting for exploration of their internal relationships. Accurately representing these spatiotemporal relationships and improving the accuracy of spatiotemporal traffic prediction are critical challenges in current intelligent transportation forecasting. To tackle this issue, we propose an intelligent prediction framework for traffic flow based on the adaptive dual-graphic transformer with a cross-fusion strategy. Our aim is to uncover latent graphic feature representations that transcend temporal and spatial limitations. Furthermore, we establish a traffic spatiotemporal prediction model using a cross-fusion attention mechanism to capture dependency relationships represented by adaptive graphs. Extensive experiments demonstrate that our proposed model achieves superior prediction performance on practical urban traffic flow datasets compared to benchmarks, particularly for long-term predictions. Further analysis confirms its strength in balancing reliability and practicality, making it well-suited for applications in intelligent transportation systems.

A novel framework for wave power plant site selection and wave forecasting based on GIS, MCDM, and ANN methods: A case study in Hainan Island, Southern China

Wave power plants (WPPs) hold significant promise for sustainable energy generation but face complex challenges in site selection and wave forecasting. To address these challenges, this study presents an integrated methodology that combines geographic information system (GIS), multi-criteria decision making (MCDM) and artificial neural network (ANN) techniques. The primary objective of this research is to identify optimal sites for WPP deployment and enhance the accuracy of wave power density (WPD) forecasting. The study focuses on Hainan Island, the second-largest island in China, and employs both macro-scale and micro-scale site selection methods. It establishes a comprehensive criteria system that encompasses environmental, technical, economic, and social aspects. To improve the objectivity of criteria weighting, a group decision making-analytic hierarchy process (GDM-AHP) approach is applied. The findings reveal that approximately 1.36 % (1427.93 km2) of Hainan Island's area offers suitable conditions for WPP deployment, with concentrations in the southern, northern, and eastern marine regions. Among the 27 identified alternative sites covering 208.76 km2 along the eastern coast, six optimal sites are pinpointed in Wanning, Wenchang, and Qionghai. Furthermore, the optimized ANN outperforms the standard ANN, achieving a mean relative error of 9.0 %. This research contributes to the theoretical understanding of WPP site selection and wave forecasting while offering a practical and adaptable framework for stakeholders involved in renewable energy projects, particularly in coastal areas such as Hainan Island. These results and methodologies have real-world implications for the efficient and effective deployment of wave energy projects, ultimately promoting sustainable energy generation and socioeconomic development.