Accuracy Of Forecasting Models Research Articles

Towards efficient model recommendation: An innovative hybrid graph neural network approach integrating multisignature analysis of electrical time series

In the energy sector, it is important to meticulously choose an accurate forecasting model because making informed decisions is crucial for optimal grid operation. This article proposes a hybrid graph neural network (GNN) that successfully captures complex patterns by combining interactions based on features and time. The proposed architecture uses diverse decomposition methods, such as statistical, dynamic, and spectral, to uncover hidden patterns. The integration of attention and graph convolution layers improves the flow of information, and the cross-modal fusion layer competently combines nodes and edges. This configuration can efficaciously assimilate disparate features, providing an advantage over other approaches. The hybrid GNN with an analytic hierarchy process (AHP) performs better than the existing models when tested exhaustively on diverse regional energy demand and pricing time series. It captures complex patterns more effectively than K-nearest neighbour (KNN), random forest regressor (RFR), and GNN-based model suggestion methods. For the nonstationary price data from New South Wales and the Punjab energy demand time series, the Kendall’s Tau coefficient is 0.73 and 0.81 and the Spearman’s Rank coefficient is 0.74 and 0.91, respectively. This paper advances the field of time series forecasting by offering a novel strategy for improving model proposals by efficiently merging hybrid GNN with multiple feature modalities.

A Deep Learning Approach Based on Novel Multi-Feature Fusion for Power Load Prediction

Adequate power load data are the basis for establishing an efficient and accurate forecasting model, which plays a crucial role in ensuring the reliable operation and effective management of a power system. However, the large-scale integration of renewable energy into the power grid has led to instabilities in power systems, and the load characteristics tend to be complex and diversified. Aiming at this problem, this paper proposes a short-term power load transfer forecasting method. To fully exploit the complex features present in the data, an online feature-extraction-based deep learning model is developed. This approach aims to extract the frequency-division features of the original power load on different time scales while reducing the feature redundancy. To solve the prediction challenges caused by insufficient historical power load data, the source domain model parameters are transferred to the target domain model utilizing Kendall’s correlation coefficient and the Bayesian optimization algorithm. To verify the prediction performance of the model, experiments are conducted on multiple datasets with different features. The simulation results show that the proposed model is robust and effective in load forecasting with limited data. Furthermore, if real-time data of new energy power systems can be acquired and utilized to update and correct the model in future research, this will help to adapt and integrate new energy sources and optimize energy management.

On Integrating Time-Series Modeling with Long Short-Term Memory and Bayesian Optimization: A Comparative Analysis for Photovoltaic Power Forecasting

The means of energy generation are rapidly progressing as production shifts from a centralized model to a fully decentralized one that relies on renewable energy sources. Energy generation is intermittent and difficult to control owing to the high variability in the weather parameters. Consequently, accurate forecasting has gained increased significance in ensuring a balance between energy supply and demand with maximum efficiency and sustainability. Despite numerous studies on this issue, large sample datasets and measurements of meteorological variables at plant sites are generally required to obtain a higher prediction accuracy. In practical applications, we often encounter the problem of insufficient sample data, which makes it challenging to accurately forecast energy production with limited data. The Holt–Winters exponential smoothing method is a statistical tool that is frequently employed to forecast periodic series, owing to its low demand for training data and high forecasting accuracy. However, this model has limitations, particularly when handling time-series analysis for long-horizon predictions. To overcome this shortcoming, this study proposes an integrated approach that combines the Holt–Winters exponential smoothing method with long short-term memory and Bayesian optimization to handle long-range dependencies. For illustrative purposes, this new method is applied to forecast rooftop photovoltaic production in a real-world case study, where it is assumed that measurements of meteorological variables (such as solar irradiance and temperature) at the plant site are not available. Through our analysis, we found that by utilizing these methods in combination, we can develop more accurate and reliable forecasting models that can inform decision-making and resource management in this field.

Forecasting model for hypoid gear elastohydrodynamic lubrication considering entrainment effect

In full consideration of time-varying meshing performance and oil film characteristics, entrainment effect on elastohydrodynamic lubrication (EHL) is developed for establishing accurate forecasting model of the complex hypoid gears. Firstly, dynamic loaded tooth contact analysis (DLTCA) is employed to determine the meshing interface kinematics, load distribution and entrainment speed under dynamic load condition. Then, entrainment speed is introduced into the EHL governing equation and accurate forecasting model is established. With accurate discretization of EHL governing equation, discrete convolution and fast Fourier transformation (DC-FFT) method is employed to compute the flank elastic deformation. Finally, a hypoid gear set in automotive industrial application is exercised to verify entrainment effect on EHL assessment in the proposed model.

Semiconductor Price Index Predicting Based on a Novel Improved AdaBoost Feature-Weighted Combination Model

The semiconductor price index serves as a vital metric for assessing technological developments and related market trends. Establishing a more accurate forecasting model for the semiconductor price index is of significant importance for analyzing the industry’s trends and market directions. In this paper, a novel framework for semiconductor price index forecasting is proposed. In addition to traditional financial data, the study introduces search engine data (Google Trends) representing investor attention, and introduces text information extracted from online news headlines reflecting major market events and government policies as independent variables. Used to predict the dependent variable: The PHLX Semiconductor Sector (SOX). First, the XGBoost model is employed to compute the importance scores of each feature. Then, a feature weight coefficient indicator is constructed based on these importance scores to calculate the weight coefficient indicator values for each feature. These indicator values are then used to weight the kernel function of Support Vector Regression (SVR), resulting in weighted Support Vector Regression (WSVR). Finally, WSVR is utilized as the base learner for Adaptive Boosting (AdaBoost), yielding the XGBoost–WSVR–AdaBoost model based on feature weighting. The proposed model outperforms AdaBoost, RNN, ERT, LSTM, and other models in terms of Mean Absolute Percentage Error (MAPE) and goodness-of-fit (R2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${R}^{2}$$\\end{document}). It also exhibits superior predictive performance compared to models in ablation experiments, and the introduction of text data or Google trends further improves the prediction performance of the model. In conclusion, the improved AdaBoost feature-weighted combination model proposed in this study offers a more accurate prediction for semiconductor price index.

Attention Based Energy Demand Forecasting in Smart Grid Environments

The smart grid is a crucial aspect of the modern energy landscape, providing a reliable, efficient, and sustainable way of meeting the growing energy demands. However, the vast amounts of data generated by smart grid technology necessitate the development of advanced data processing and analysis techniques. In this paper, we propose an attention-based time series workflow that combines dilated convolution and attention mechanisms for time series forecasting in smart grid applications. This workflow extracts temporal features from time series data using dilated convolutions and emphasizes significant temporal points in the hidden states using attention mechanisms. Experimental evaluations showed up to an 8% better performance for energy demand forecasting compared to commonly used deep learning-based methods. Note that our workflow achieved this gain by requiring 1/3 of the training time other models took. We have also improved performance by 42% in various domains, demonstrating the adaptability of our approach across different areas. This study may assist researchers in constructing accurate forecasting models for smart grid environments. Furthermore, it highlights that the attention-based approach can be employed to promote sustainable energy and optimize smart grid environments.

Temporal-spatial dependencies enhanced deep learning model for time series forecast

Forecasting financial time series can be challenging because of the inherent complex interplay of temporal and spatial dynamics in the data. Specifically, time series for different geographical locations often have different yet inter-dependent patterns; even for the same-location time series, patterns can vary over time. Therefore, an accurate forecasting model has to take both temporal and spatial patterns into consideration. This study proposes a new model named Temporal-Spatial dependencies ENhanced deep learning model (TSEN), which consists of multiple RNN-based layers and an attention layer: each RNN-based layer learns the temporal pattern of a specific time series at the presence of multivariate exogenous series, and the attention layer learns the spatial correlative weight and obtains the global representations simultaneously. We illustrate the use of TSEN in forecasting household leverage time series in China. We show that clustering and choosing correlative series are necessary steps to obtain accurate forecast. The results show that the proposed method captures the temporal-spatial dynamics of household leverage and generates more accurate prediction than traditional methods.

Flood Prediction System Using IOT & Artificial Neural Network

Floods pose significant challenges as one of nature's most devastating disasters, making the development of accurate forecast model’s complex. This issue has led to severe consequences such as crop loss, population displacement, damage to infrastructure, and disruption of essential services. Advanced research on flood prediction models has played a crucial role in providing policy recommendations, mitigating risks, reducing human casualties, and minimizing property damage caused by floods. In this context, we propose an Internet of Things (IoT)-based flood prediction and forecasting model that prioritizes energy efficiency. Given the limited battery and memory capacity of IoT sensor nodes, we employ an energy-saving strategy within the fog layer, leveraging data diversity to minimize energy consumption. Additionally, cloud technology offers an effective storage solution. To accurately calibrate flood phases, we investigate climatic factors such as humidity, temperature, rainfall, as well as water body parameters including water flow and elevation. Neural networks are commonly used in constructing forecast systems, as they can replicate the complex calculations involved in flood physical processes, resulting in improved performance and cost-effectiveness. In our approach, the Artificial Neural Network (ANN) technique is employed for flood forecasting, and the effectiveness of different algorithms, such as Logistic Regression and Decision Tree, is assessed by comparing them to ANN. Accuracy values are computed using a classification report assessment, and graph parameters are carefully evaluated. Ultimately, our proposed system utilizes the ANN technique to train a predictive model by examining the dataset. This model generates real-time flood risk forecasts through a user-friendly graphical interface.

Machine learning-based fracturing parameter optimization for horizontal wells in Panke field shale oil

In the process of developing tight oil and gas reservoirs, multistage fractured horizontal wells (NFHWs) can greatly increase the production rate, and the optimal design of its fracturing parameters is also an important means to further increase the production rate. Accurate production prediction is essential for the formulation of effective development strategies and development plans before and during project execution. In this study, a novel workflow incorporating machine learning (ML) and particle swarm optimization algorithms (PSO) is proposed to predict the production rate of multi-stage fractured horizontal wells in tight reservoirs and optimize the fracturing parameters. The researchers conducted 10,000 numerical simulation experiments to build a complete training and validation dataset, based on which five machine learning production prediction models were developed. As input variables for yield prediction, eight key factors affecting yield were selected. The results of the study show that among the five models, the random forest (RF) model best establishes the mapping relationship between feature variables and yield. After verifying the validity of the Random Forest-based yield prediction model, the researchers combined it with the particle swarm optimization algorithm to determine the optimal combination of fracturing parameters under the condition of maximizing the net present value. A hybrid model, called ML-PSO, is proposed to overcome the limitations of current production forecasting studies, which are difficult to maximize economic returns and optimize the fracturing scheme based on operator preferences (e.g., target NPV). The designed workflow can not only accurately and efficiently predict the production of multi-stage fractured horizontal wells in real-time, but also be used as a parameter selection tool to optimize the fracture design. This study promotes data-driven decision-making for oil and gas development, and its tight reservoir production forecasts provide the basis for accurate forecasting models for the oil and gas industry.

Information Entropy-Based Hybrid Models Improve the Accuracy of Reference Evapotranspiration Forecast

Accurate forecasting of reference crop evapotranspiration (ET0) is vital for sustainable water resource management. In this study, four popularly used single models were selected to forecast ET0 values, including support vector regression, Bayesian linear regression, ridge regression, and lasso regression models, respectively. They all had advantages of low requirement of data input and good capability of data fitting. However, forecast errors inevitably existed in those forecasting models due to data noise or overfitting. In order to improve the forecast accuracy of models, hybrid models were proposed to integrate the advantages of the single models. Before the construction of hybrid models, each single model’s weight was determined based on two weight determination methods, namely, the variance reciprocal and information entropy weighting methods. To validate the accuracy of the proposed hybrid models, 1–30 d forecast data from January 2 to February 1, 2022, were used as a test set in Xinxiang, North China Plain. The results confirmed the feasibility of the information entropy-based hybrid model. In detail, the information entropy model generated the mean absolute percentage errors of 11.9% or a decrease by 48.9% compared to the single and variance reciprocal hybrid models. Moreover, the model generated a correlation coefficient of 0.90 for 1–30 d ET0 forecasting or an increase by 13.6% compared to other models. The standard deviation and the root mean square error of the information entropy model were 1.65 mm·d−1 and 0.61 mm·d−1 or had a decrease by 16.4% and 23.7%. The maximum precision and the F1 score were 0.9618 and 0.9742 for the information entropy model. It was concluded that the information entropy-based hybrid model had the best midterm (1–30 d) ET0 forecasting performance in the North China Plain.

Robust Multi-Dimensional Time Series Forecasting.

Large-scale and high-dimensional time series data are widely generated in modern applications such as intelligent transportation and environmental monitoring. However, such data contains much noise, outliers, and missing values due to interference during measurement or transmission. Directly forecasting such types of data (i.e., anomalous data) can be extremely challenging. The traditional method to deal with anomalies is to cut out the time series with anomalous value entries or replace the data. Both methods may lose important knowledge from the original data. In this paper, we propose a multidimensional time series forecasting framework that can better handle anomalous values: the robust temporal nonnegative matrix factorization forecasting model (RTNMFFM) for multi-dimensional time series. RTNMFFM integrates the autoregressive regularizer into nonnegative matrix factorization (NMF) with the application of the L2,1 norm in NMF. This approach improves robustness and alleviates overfitting compared to standard methods. In addition, to improve the accuracy of model forecasts on severely missing data, we propose a periodic smoothing penalty that keeps the sparse time slices as close as possible to the time slice with high confidence. Finally, we train the model using the alternating gradient descent algorithm. Numerous experiments demonstrate that RTNMFFM provides better robustness and better prediction accuracy.

The Accuracy of Predictive Analytics in Forecasting Emergency Department Volume Before and After Onset of COVID-19.

Big data and improved analytic techniques, such as triple exponential smoothing (TES), allow for prediction of emergency department (ED) volume. We sought to determine 1)which method of TES was most accurate in predicting pre-coronavirus 2019 (COVID-19), during COVID-19, and post-COVID-19 ED volume; 2)how the pandemic would affect TES prediction accuracy; and 3)whether TES would regain its pre-COVID-19 accuracy in the early post-pandemic period. We studied monthly volumes of four EDs with a combined annual census of approximately 250,000 visits in the two years prior to, during the 25-month COVID-19 pandemic, and the 14 months following. We compared the accuracy of four models of TES forecasting by measuring the mean absolute percentage error (MAPE), mean square errors (MSE) and mean absolute deviation (MAD), comparing actual to predicted monthly volume. In the 23 months prior to COVID-19, the overall average MAPE across four forecasting methods was 3.88% ± 1.88% (range 2.41-6.42% across the four ED sites), rising to 15.21% ± 6.67% during the 25-month COVID-19 period (range 9.97-25.18% across the four sites), and falling to 6.45% ± 3.92% in the 14 months after (range 3.86-12.34% across the four sites). The 12-month Holt-Winter method had the greatest accuracy prior to COVID-19 (3.18% ± 1.65%) and during the pandemic (11.31% ± 4.81%), while the 24-month Holt-Winter offered the best performance following the pandemic (5.91% ± 3.82%). The pediatric ED had an average MAPE more than twice that of the average MAPE of the three adult EDs (6.42% ± 1.54% prior to COVID-19, 25.18% ± 9.42% during the pandemic, and 12.34% ± 0.55% after COVID-19). After the onset of the pandemic, there was no immediate improvement in forecasting model accuracy until two years later; however, these still had not returned to baseline accuracy levels. We were able to identify a TES model that was the most accurate. Most of the models saw an approximate four-fold increase in MAPE after onset of the pandemic. In the months following the most severe waves of COVID-19, we saw improvements in the accuracy of forecasting models, but they were not back to pre-COVID-19 accuracies.

Искусственный интеллект в глобальной логистике

In the article, through theoretical analysis and research of logistics development indicators in modern companies, the importance and features of the introduction of artificial intelligence are determined. Artificial intelligence (AI) is considered one of the most revolutionary technologies in modern history. Enterprises use AI to optimize their resources and improve operational efficiency. For companies wishing to introduce new technologies, artificial intelligence offers many advantages. AI has wide applications in supply chains and logistics. It is applied using many different applications that are used all over the world. The desire to remain competitive leads enterprises to decide to use more high-precision, modern equipment to improve production operations. The industry leaders are the companies that apply the latest technologies most decisively. Innovative solutions increase the efficiency of management tasks, which include prompt order fulfillment, improved inventory accuracy, shorter delivery times and more accurate forecasting models. The study helped to identify not only the advantages and benefits of implementing AI in enterprises, but also possible risks. A thorough examination has been conducted on the digital transformation within the multimodal transport corridors of the Republic of Kazakhstan. This transformation is intended to be implemented through cutting-edge technological advancements and adherence to standards, in collaboration with the business community encompassing trade, IT, and the transportation sector. Using SWOT analysis, the consequences of the introduction of AI have been studied both at the mycological and macrological levels of enterprise functioning. Based on all the studied data, the indicators that a company must have in order to implement an innovative technology called Artificial Intelligence are presented.

An AI-Based System for Predicting Renewable Energy Power Output Using Advanced Optimization Algorithms

Accurate generation forecasting of Renewable Energy Sources (RES) is becoming more and more crucial for effective grid operation and energy management as RES are incorporated into the electrical grid. Because Machine Learning (ML) and Deep Learning (DL) algorithms can learn complicated relationships from data and provide accurate forecasts, they have become more popular than traditional forecasting approaches, which have limits. This article examines the state of the art and future directions in the field of ML and DL-based forecasting of renewable energy generation. This paper reviews the several approaches and models that have been used to project renewable energy. It also highlights the challenges, such as managing the uncertainty and unpredictability of renewable energy output, data accessibility, and model interpret ability. To sum up, this study emphasizes how important it is to develop accurate and dependable renewable energy forecasting models to facilitate the future transition to sustainable energy sources and enable the integration of RES into the electrical grid.

FRACTAL MARKET HYPOTHESIS FOR TRADING AND MARKET PRICE FORECAST

The article explores the core principles of FMH and its application in trading and market price forecasting. FMH offers a new perspective for understanding market dynamics, allowing for the detection of patterns that traditional analysis methods often overlook. Special emphasis is placed on the scaling properties of market data, which enables the use of forecasting models across different time intervals, from short-term to long-term predictions. FMH also considers the probability of extreme events, enhancing risk assessment and improving forecasting accuracy. The article discusses the advantages of the Fractal Market Hypothesis compared to traditional financial hypotheses, such as the Random Walk Hypothesis and the Efficient Market Hypothesis, and its potential for integration with machine learning methods to create more accurate and reliable forecasting models.

Enhancing short-term streamflow forecasting of extreme events: A wavelet-artificial neural network hybrid approach

Accurate short-term streamflow forecasting models are crucial for effective water resource management, enabling timely responses to extreme flood or drought events and mitigating potential socioeconomic damage. This study proposes robust hybrid Wavelet Artificial Neural Network (WANN) models for real-world hydrological applications. Two WANN variants, WANNone and WANNmulti, are proposed for short-term streamflow forecasting of extreme (high and low) flows at eight gauging stations within Brazil's Paraíba do Sul River basin. WANNone directly feeds both the original streamflow data and the decomposed components obtained through an À Trous wavelet transform into the ANN architecture. Conversely, WANNmulti utilizes separate ANNs for the original data, with the final streamflow estimate reconstructed via the inverse wavelet transform of the individual ANN outputs. The performance of these WANN models is then compared against conventional ANN models. In both approaches, Bayesian optimization is employed to fine-tune the hyperparameters within the ANN architecture. The WANN models achieved superior performance for 7-day streamflow forecasts compared to conventional ANN models. WANN models yielded high R2 values (>0.9) and low MAPE (4.8%–14.7%) within the expected RMSE range, demonstrating statistically significant improvements over ANN models (71% and 75% reduction in RMSE and MAPE, respectively, and 69% increase in R2). Further analysis revealed that WANNmulti models generally exhibited superior performance for low extreme flow predictions, while WANNone models achieved the highest accuracy for high extreme flows at most stations. WANN models' strong performance suggests their value for real-time flood warnings, enabling improved decision-making in areas like flood/drought mitigation and urban water planning.

Inventory Optimization Using Data Science Technologies for Supply Chain 4.0

In the context of supply chain 4.0, Data Science (DS) can improve operations and inventory management by using statistical and machine learning techniques. Additionally, big data can reveal valuable insights for predictive and prescriptive analytics, which can aid in enhancing competitiveness in today’s business environment. Accurate demand forecasting in supply chain inventory is a fundamental step to improve inventory management, address ordering uncertainties, and minimize costs while meeting customer demands. This requires the efficient use of demand forecasting tools, assessing predictive data analysis techniques. Challenges can arise from inefficient ordering models, selecting accurate forecasting models, and considering issues like over-and underestimation leading to food waste and profit margin impacts, particularly for products with short shelf life. Other challenges include enhancing inventory optimization efficiency, adapting to dynamic demands, and formulating optimal inventory decisions. In this work, we introduce a supply chain 4.0 inventory management approach, where we combined DS techniques, predictive analytics, and big data approach to enhance inventory control. A prediction model is also introduced in order to forecast incoming and outgoing inventory. This model is based on a detailed dataset that takes into account the districts and seasons data. The model’s performance was evaluated based on performance measurements, such as Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). Significantly, the results show that the random forest algorithm was the best in predicting OUT inventory quantities with an average error equal to 0.011, while the linear regression algorithm produced the best performance in predicting IN inventory quantities with an average error of 0.03

Ultra-short-term solar forecasting with reduced pre-acquired data considering optimal heuristic configurations of deep neural networks

<abstract> <p>Forecasting solar irradiance, particularly Global Horizontal Irradiance (GHI), has drawn much interest recently due to the rising demand for renewable energy sources. Many works have been proposed in the literature to forecast GHI by incorporating weather or environmental variables. Nevertheless, the expensive cost of the weather station hinders obtaining meteorological data, posing challenges in generating accurate forecasting models. Therefore, this work addresses this issue by developing a framework to reliably forecast the values of GHI even if meteorological data are unavailable or unreliable. It achieves this by leveraging lag observations of GHI values and applying feature extraction capabilities of the deep learning models. An ultra-short-term GHI forecast model is proposed using the Convolution Neural Network (CNN) algorithm, considering optimal heuristic configurations. In addition, to assess the efficacy of the proposed model, sensitivity analysis of different input variables of historical GHI observations is examined, and its performance is compared with other commonly used forecasting algorithm models over different forecasting horizons of 5, 15, and 30 minutes. A case study is carried out, and the model is trained and tested utilizing real GHI data from solar data located in Riyadh, Saudi Arabia. Results reveal the importance of employing historical GHI data in providing precise forecasting outcomes. The developed CNN-based model outperformed in ultra-short-term forecasting, showcasing average root mean square error results across different forecasting horizons: 2.262 W/m<sup>2</sup> (5min), 30.569 W/m<sup>2</sup> (15min), and 54.244 W/m<sup>2</sup> (30min) across varied day types. Finally, the findings of this research can permit GHI to be integrated into the power grid and encourage the development of sustainable energy systems.</p> </abstract>

Validation of methods for developing typical meteorological years based on future climate models

You Buildings designed for coming decades are more susceptible to global warming, rising average temperatures, and heat waves, which are of a greater risk than in the 1990s. Simulation-based design decisions may be inaccurate if just historical data is used to generate climate files. The building's energy performance, cooling and heating system’s design, and room unit sizing require reliable weather data. So far mainly historic meteorological data has been used for simulations. Annual simulations and cooling/heating system design often use a typical meteorological year (TMY) based on historical data using ISO 15927-4 and ISO 15927-2 thorough instructions for TMY for annual simulations and design day data. The above climate models lack the data needed to construct TMYs for building performance simulation (BPS) tools. Climate model forecast accuracy must also be examined from the BPS perspective. This work aims to illustrate and test methods for producing TMYs using three climate models with different resolution and modality in Tartu, Estonia, from 1985 to 2015. The ISO 15927-4 approach selected months from historical meteorological data appropriate for each climate model. Three BPS TMYs were created, and a reference building's energy needs simulated. Long-term historical data was used to simulate the reference building's energy requirement and develop TMYs. The results showed that all the TMYs developed based on NorESM, MPIESM and ECEarth climate models can represent well the energy needs obtained with the TMY based on historical weather data depending on the TMY generation method while MPIESM shows deficiency in cooling season. TMY based on NorESM have the most consistent energy need simulation results while TMY based on ECEarth also performs well both for predicting cooling and heating needs. The future work includes finding other suitable methods for TMY generation that results in even less errors for all models and further validation with other reference buildings for final climate model selection to develop future climate scenarios.

Improving Model Forecast Accuracy by Assimilating Brightness Temperature of FY-4B AGRI Water Vapor Channels Using the GSI-based 3DVar Approach

Improving Model Forecast Accuracy by Assimilating Brightness Temperature of FY-4B AGRI Water Vapor Channels Using the GSI-based 3DVar Approach