A Multi-Farm Global-to-Local Expert-Informed Machine Learning System for Strawberry Yield Forecasting DOI Creative Commons
Matthew Beddows, Georgios Leontidis

Agriculture, Journal Year: 2024, Volume and Issue: 14(6), P. 883 - 883

Published: June 2, 2024

The importance of forecasting crop yields in agriculture cannot be overstated. effects yield are observed all the aspects supply chain from staffing to supplier demand, food waste, and other business decisions. However, process is often inaccurate far perfect. This paper explores potential using expert forecasts enhance predictions our global-to-local XGBoost machine learning system. Additionally, it investigates ERA5 climate model’s viability as an alternative data source for absence on-farm weather data. We find that, by combining both expert’s pre-season model with model, we can—in most cases—obtain better that outperform growers’ learning-only models. Our expert-informed attains 4 weeks ahead average RMSE 0.0855 across plots 0.0872 included.

Language: Английский

Evaluating the Accuracy of the ERA5 Model in Predicting Wind Speeds Across Coastal and Offshore Regions DOI Creative Commons
Mohamad Alkhalidi,

Abdullah N. Al–Dabbous,

Shoug Kh. Al-Dabbous

et al.

Journal of Marine Science and Engineering, Journal Year: 2025, Volume and Issue: 13(1), P. 149 - 149

Published: Jan. 16, 2025

Accurate wind speed and direction data are vital for coastal engineering, renewable energy, climate resilience, particularly in regions with sparse observational datasets. This study evaluates the ERA5 reanalysis model’s performance predicting speeds directions at ten offshore stations Kuwait from 2010 to 2017. analysis reveals that effectively captures general patterns, demonstrating stronger correlations (up 0.85) higher Perkins Skill Score (PSS) values 0.94). However, model consistently underestimates variability extreme events, especially stations, where correlation coefficients dropped 0.35. Wind highlighted ERA5’s ability replicate dominant northwest patterns. it notable biases underrepresented during transitional seasons. Taylor diagrams error metrics further emphasize challenges capturing localized dynamics influenced by land-sea interactions. Enhancements such as calibration using high-resolution datasets, hybrid models incorporating machine learning techniques, long-term monitoring networks recommended improve accuracy. By addressing these limitations, can more support engineering applications, including infrastructure design energy development, while advancing Kuwait’s sustainable development goals. provides valuable insights into refining complex environments.

Language: Английский

Citations

3
Understanding “8.12” Flash Flood in Suizhou, China: A Meteorological Analysis and Implications for Multi-scale Prevention Strategies DOI

Enze Jin,

Xiekang Wang

International Journal of Disaster Risk Reduction, Journal Year: 2025, Volume and Issue: unknown, P. 105397 - 105397

Published: March 1, 2025

Language: Английский

Citations

0
Development of a fast radiative transfer model for ground-based microwave radiometers (ARMS-gb v1.0): validation and comparison to RTTOV-gb DOI Creative Commons
Yi‐Ning Shi, Jun Yang, Wei Han

et al.

Geoscientific model development, Journal Year: 2025, Volume and Issue: 18(6), P. 1947 - 1964

Published: March 25, 2025

Abstract. This study proposes a fast radiative transfer model, the Advanced Radiative Transfer Modeling System – ground-based (ARMS-gb), designed to simulate brightness temperatures observed by microwave radiometers. ARMS-gb employs clear-sky solver account for atmospheric thermal emissions, while gaseous absorption is estimated using statistical regression scheme. To enhance simulation accuracy, particularly in moist environments, seven humid profiles from University of Maryland, Baltimore County 48-profile dataset are added European Centre Medium-Range Weather Forecasts 83-profile train Additionally, an advanced water vapor vertical interpolation method incorporated, offering improved accuracy compared used TOVS (RTTOV)-gb. The standard deviation reduced 0.15 K channels with strong absorption. Jacobians calculated these two modes also different. further validate ARMS-gb's performance, simulations both and RTTOV-gb against real observations observation minus background analyses demonstrates that aligns well achieves smaller deviations under high-humidity conditions. Furthermore, capability monitor observational quality radiometers demonstrated.

Language: Английский

Citations

0
Unveiling the intricate dynamics of PM2.5 sulfate aerosols in the urban boundary layer: A pioneering two-year vertical profiling and machine learning-enhanced analysis in global Mega-City DOI
Hongyi Li, Ting Yang, Yifan Song

et al.

Urban Climate, Journal Year: 2025, Volume and Issue: 61, P. 102424 - 102424

Published: April 16, 2025

Language: Английский

Citations

0
Combined Wind Turbine Protection System DOI Creative Commons
Vladimir Kaverin, Gulim Nurmaganbetova, Gennadiy Em

et al.

Energies, Journal Year: 2024, Volume and Issue: 17(20), P. 5074 - 5074

Published: Oct. 12, 2024

The increasing deployment of wind turbines in technologically advanced nations underscores the need to enhance their reliability, extend operational lifespan, and minimize failures. current protection devices for turbine components do not sufficiently shield them from various external factors that degrade performance. This study addresses environmental technical challenges disrupt operations reviews existing research solutions protecting individual components, supported by experimental findings. Using a decomposition method followed integration we propose combined system designed improve overall resilience turbines. proposed aims reduce incidents, service life, increase addressing critical gap energy technology contributing its continued development efficiency.

Language: Английский

Citations

1
A Multi-Farm Global-to-Local Expert-Informed Machine Learning System for Strawberry Yield Forecasting DOI Creative Commons
Matthew Beddows, Georgios Leontidis

Agriculture, Journal Year: 2024, Volume and Issue: 14(6), P. 883 - 883

Published: June 2, 2024

The importance of forecasting crop yields in agriculture cannot be overstated. effects yield are observed all the aspects supply chain from staffing to supplier demand, food waste, and other business decisions. However, process is often inaccurate far perfect. This paper explores potential using expert forecasts enhance predictions our global-to-local XGBoost machine learning system. Additionally, it investigates ERA5 climate model’s viability as an alternative data source for absence on-farm weather data. We find that, by combining both expert’s pre-season model with model, we can—in most cases—obtain better that outperform growers’ learning-only models. Our expert-informed attains 4 weeks ahead average RMSE 0.0855 across plots 0.0872 included.

Language: Английский

Citations

0