Explainable Soybean Futures Price Forecasting Based on Multi‐Source Feature Fusion DOI Open Access
Binrong Wu, Sihao Yu,

Sheng‐Xiang Lv

et al.

Journal of Forecasting, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 24, 2024

ABSTRACT The prediction and early warning of soybean futures prices have been even more crucial for the formulation food‐related policies trade risk management. Amid increasing geopolitical conflicts uncertainty in across countries recent years, there significant fluctuations global prices, making it necessary to investigate reveal price determination mechanism, accurately predict trends future prices. Therefore, this study proposes a comprehensive interpretable framework forecasting. Specifically, employs set methodologies. Using snow ablation optimizer (SAO), improves parameters time fusion transformer (TFT) model, an advanced predictive model based on self‐attention mechanism. Besides, addresses factors influencing constructs effective features through feature method. To explore volatility trends, original series are decomposed using variational mode decomposition (VMD). This also enhances accuracy predictions by introducing coefficients trading volumes as predictors. empirical findings suggest that VMD‐SAO‐TFT interpretability, offering implications decision‐makers achieve accurate agricultural

Language: Английский

A Novel Double Machine Learning Strategy for Producing High‐Precision Multi‐Source Merging Precipitation Estimates Over the Tibetan Plateau DOI Creative Commons
Yi Lyu, Bin Yong

Water Resources Research, Journal Year: 2024, Volume and Issue: 60(4)

Published: April 1, 2024

Abstract Precipitation estimation over the Tibetan Plateau is a critical but challenging task due to sparse gauges and high altitudes. Traditional statistic methods are often insufficient characterize nonlinear relationship between different precipitation information, while machine learning techniques, particularly deep algorithms, offer novel powerful approach improve merging accuracy of multi‐source data by efficiently capturing their spatiotemporal dynamics features. This study introduced strategy called Double Machine Learning (DML), which integrates meteorological satellite retrievals, reanalysis produce high‐precision product at 0.1° × 0.1°, daily resolution for Plateau. The quantitative evaluation DML was accomplished using both auto‐meteorological independent observations. Statistical scores indicate that new DML‐based apparently outperforms three widely‐used datasets (IMERG‐Final, GSMaP‐Gauge ERA5) proposed effectively advantages traditional learning, significantly enhancing algorithmic robustness accuracy, medium‐high rain rates in summer. Furthermore, contributions inputs final effect systematically analyzed. It found as an auxiliary variable DML, plays crucial role identifying rainy events adjusting bias estimates, especially those ungauged regions. affirms call improving estimates combining approaches. reported here recommended hydrometeorological users science community.

Language: Английский

Citations

12
The Impact of Climate Change on Construction Activity Performance DOI Creative Commons
Sertaç Oruç,

Huseyin Attila Dikbas,

Berkin Gümüş

et al.

Buildings, Journal Year: 2024, Volume and Issue: 14(2), P. 372 - 372

Published: Jan. 31, 2024

There are specific construction operations that require weather forecast data to make short-term decisions regarding construction; however, most resource-related decision making and all project management plans must be carried out anticipate conditions beyond the capabilities of currently available forecasting technologies. In this study, a series single- multi-risk analyses were performed with ~9 km grid resolution over Türkiye using combinations climate variables their threshold values which have an impact on execution performance activities. These will improve predictability potential delays, enable scheduled future-proof basis by considering calculated normal periodic predictions scale, serve as dispute tool for related claims. A comprehensive case study showcasing methodology illustrating its application shows duration is expected extended because both historical future periods. While original was 207 days, when effects considered, optimum mean median increased 255 238 respectively, period. The change 239 days end century, according SSP5-8.5 scenario, if schedules consider change. in mainly due rising temperatures, winter workability reduced summer workability. However, practices schedules, increase 258 244 may cause unavoidable direct, indirect, or overhead costs.

Language: Английский

Citations

9
A hybrid framework for regional climate seasonality study and trend analysis DOI

Masooma Suleman,

Peter A. Khaiter

Environmental Modelling & Software, Journal Year: 2025, Volume and Issue: unknown, P. 106429 - 106429

Published: March 1, 2025

Language: Английский

Citations

0
Evaluation of precipitation forecasting base on GraphCast over mainland China DOI Creative Commons

Zihuang Yan,

Xianghui Lu, Lifeng Wu

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 28, 2025

The accurate cumulative precipitation forecasts are essential for monitoring water resources and natural disasters. combination of deep learning big data has become a new direction forecasting. However, the current large models still lacking in-situ verification. To accomplish this goal, forecasting performance state-of-the-art model GraphCast was evaluated. Using from 2393 observation stations 1-3 day period as reference, we assessed in mainland China region 2020 to 2021, utilizing high-resolution with 0.25° × grid spacing 13 layers parameters. European Centre Medium-Range Weather Forecasts (ECMWF) also compared. results show that: (1) During 2020-2021 period, 1-day, 2-day, 3-day forecasts, Root Mean Square Error (RMSE) values were primarily between 0.46 9.38 mm/d, 0.44 9.06 respectively. (ME) mainly - 0.595 1.705 (0.01 mm). (2) As forecast extends, capability declines. (3) In various China, demonstrates higher predictive accuracy than ECMWF. (4) Compared ECMWF, demonstrated best temperate humid semi-humid regions Northeast RMSE being approximately 12% higher. Our study indicates that significant potential

Language: Английский

Citations

0
Artificial Intelligence and Numerical Weather Prediction Models: A Technical Survey DOI Creative Commons
Muhammad Waqas, Usa Wannasingha Humphries, Bunthid Chueasa

et al.

Natural Hazards Research, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 1, 2024

Language: Английский

Citations

3
Ensemble post-processing of sub-seasonal to seasonal precipitation forecasts based on a novel probabilistic double machine learning method DOI
Shaojie Zhan, Aizhong Ye, Lingyun Wu

et al.

Journal of Hydrology, Journal Year: 2025, Volume and Issue: unknown, P. 133484 - 133484

Published: May 1, 2025

Language: Английский

Citations

0
Machine learning‐based streamflow forecasting using CMIP6 scenarios: Assessing performance and improving hydrological projections and climate change DOI Creative Commons
Veysi Kartal

Hydrological Processes, Journal Year: 2024, Volume and Issue: 38(6)

Published: June 1, 2024

Abstract Water is essential for humans as well all living organisms to sustain their lives. Therefore, any climate‐driven change in available resources has significant impacts on the environment and life. Global climate models (GCMs) are one of most practical methods evaluate change. Based this, this research evaluated capability GCMs from Coupled Model Intercomparison Project 6 (CMIP6) reproduce historical flow prediction centre data Konya Closed basin project using selected GCMs. based CMIP6 under scenario common socioeconomic pathways (SSP245 SSP 585) were used analyse effect streamflow study area by Bias Correction GCM Models Long Short‐Term Memory (LSTM), Bidirectional LSTM (BiLSTM), AdaBoost, Gradient Boosting, Regression Tree, Random Forest methods. The coefficient determination (R 2 ), mean square error (MSE), absolute (MAE), root (RMSE) assess performance Findings show that consistently outperformed other both testing training phases. A downward volume water flowing through region's rivers streams next decades. It critical enhance climate‐resilient infrastructure financing, establish an early warning system drought, introduce best management practices, implement integrated resource management, public awareness, support alleviate negative consequences drought increase resilience against effects Turkey's resources.

Language: Английский

Citations

2
Comparative study of cloud evolution for rainfall nowcasting using AI-based deep learning algorithms DOI
X. S. Jiang,

Ji Chen,

Xunlai Chen

et al.

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 639, P. 131593 - 131593

Published: July 2, 2024

Language: Английский

Citations

2
Recent Applications of Explainable AI (XAI): A Systematic Literature Review DOI Creative Commons
Mirka Saarela, Vili Podgorelec

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(19), P. 8884 - 8884

Published: Oct. 2, 2024

This systematic literature review employs the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to investigate recent applications of explainable AI (XAI) over past three years. From an initial pool 664 articles identified through Web Science database, 512 peer-reviewed journal met inclusion criteria—namely, being recent, high-quality XAI application published in English—and were analyzed detail. Both qualitative quantitative statistical techniques used analyze articles: qualitatively by summarizing characteristics included studies based on predefined codes, quantitatively analysis data. These categorized according their domains, techniques, evaluation methods. Health-related particularly prevalent, with a strong focus cancer diagnosis, COVID-19 management, medical imaging. Other significant areas environmental agricultural industrial optimization, cybersecurity, finance, transportation, entertainment. Additionally, emerging law, education, social care highlight XAI’s expanding impact. The reveals predominant use local explanation methods, SHAP LIME, favored its stability mathematical guarantees. However, critical gap results is identified, as most rely anecdotal evidence or expert opinion rather than robust metrics. underscores urgent need standardized frameworks ensure reliability effectiveness applications. Future research should developing comprehensive standards improving interpretability explanations. advancements are essential addressing diverse demands various domains while ensuring trust transparency systems.

Language: Английский

Citations

2
Evaluation Method of Severe Convective Precipitation Based on Dual-Polarization Radar Data DOI Open Access

Zhengyang Tang,

Xinyu Chang,

Xiu Ni

et al.

Water, Journal Year: 2024, Volume and Issue: 16(8), P. 1136 - 1136

Published: April 17, 2024

With global warming and intensified human activities, extreme convective precipitation has become one of the most frequent natural disasters. An accurate reliable assessment severe events can support social stability economic development. In order to investigate accuracy enhancement methods data fusion strategies for events, this study is driven by horizontal reflectance factor (ZH) differential (ZDR) dual-polarization radar. This research work utilizes microphysical information storms provided radar variables construct event model. Considering problems high dimensionality variable low computational efficiency, proposes a echo-data-layering strategy. Combined with results mutual (MI), constructs Bayes–Kalman filter (KF) models (RF, SVR, GRU, LSTM) events. Finally, comparatively analyzes evaluation effectiveness efficiency different models. The show that data-layering strategy able reduce dimensions 256 × 34,978 5 2213, which greatly improves efficiency. addition, correlation coefficient interval III–V calibration period increased 0.9, overall model good. Among them, Bayes–KF-LSTM best effect, Bayes–KF-RF highest Further, five typical are selected validation in study. stratified dataset agrees well near-surface precipitation, model’s values close observed values. completely offered dual-polarized ZH ZDR assessment, provides wide range application possibilities

Language: Английский

Citations

1