Runoff Prediction for Hydrological Applications Using an INFO-Optimized Deep Learning Model DOI Open Access
Weisheng Wang,

Yongkang Hao,

Xiaozhen Zheng

et al.

Processes, Journal Year: 2024, Volume and Issue: 12(8), P. 1776 - 1776

Published: Aug. 22, 2024

Runoff prediction is essential in water resource management, environmental protection, and agricultural development. Due to the large randomness, high non-stationarity, low accuracy of nonlinear effects traditional model, this study proposes a runoff model based on improved vector weighted average algorithm (INFO) optimize convolutional neural network (CNN)-bidirectional long short-term memory (Bi-LSTM)-Attention mechanism. First, historical data are analyzed normalized. Secondly, CNN combined with Attention used extract depth local features input weights Bi-LSTM. Then, Bi-LSTM time series feature analysis from both positive negative directions simultaneously. The INFO parameters optimized provide optimal parameter guarantee for CNN-Bi-LSTM-Attention model. Based hydrology station’s level flow data, influence three main models two optimization algorithms compared analyzed. results show that fitting coefficient, R2, proposed 0.948, which 7.91% 3.38% higher than CNN-Bi-LSTM, respectively. R2 vector-weighted 0.993, 0.61% Bayesian (BOA), indicating method adopted paper has more significant forecasting ability can be as reliable tool long-term prediction.

Language: Английский

A Review of Earth-Air Heat Exchangers: From Fundamental Principles to Hybrid Systems with Renewable Energy Integration DOI Creative Commons
Hanna Koshlak

Energies, Journal Year: 2025, Volume and Issue: 18(5), P. 1017 - 1017

Published: Feb. 20, 2025

Earth-Air Heat Exchangers (EAHEs) provide a compelling solution for improving building energy efficiency by harnessing the stable subterranean temperature to pre-treat ventilation air. This comprehensive review delves into foundational principles of EAHE operation, meticulously examining heat and mass transfer phenomena at ground-air interface. study investigates impact key factors, including soil characteristics, climatic conditions, crucial system design parameters, on overall performance. Beyond independent applications, this explores integration EAHEs with diverse array renewable technologies, such as air-source pumps, photovoltaic thermal (PVT) panels, wind turbines, fogging systems, water spray channels, solar chimneys, systems. exploration aims clarify potential hybrid systems in achieving enhanced efficiency, minimizing environmental impact, robustness system.

Language: Английский

Citations

1
The Bio Steel Cycle Meets Indoor Farming - CCUS with the SusCiP Principle in Agriculture DOI Creative Commons
Sandra Kiessling

Advances in Environmental and Engineering Research, Journal Year: 2025, Volume and Issue: 06(01), P. 1 - 18

Published: Jan. 15, 2025

The World climate is changing, with a great impact on global food production systems. Extreme weather events, floods, wildfires and draughts are phenomena of disrupted previously stable natural patterns, which vital for crop animal husbandry alike. Most the World’s produced in temperate climatic zones rich arable land those affected by increasing unpredictability naturally occurring seasons conditions. This work aims to provide possible sustainable solution challenges under pressures change. Changing methods moving indoor agriculture poses immense opportunities at same time. Technical solutions currently researched explored innovators, governments industry leaders developed Bio Steel Cycle can be seen as nucleus other industries, including production, could starting point new standard all systems: SusCip principle.

Language: Английский

Citations

0
Assessment of Azerbaijan's geothermal potential for enhanced greenhouse heating systems DOI Open Access
A.Sh. Mukhtarov, Fuad Mammadov, Sevinc Malik Abasova

et al.

EUREKA Physics and Engineering, Journal Year: 2025, Volume and Issue: 1, P. 24 - 33

Published: Jan. 31, 2025

The appropriate use of geothermal energy, a notable renewable resource, presents considerable potential for greenhouse heating, particularly in areas such as Azerbaijan, which has abundant resources. This article examines the utilization energy emphasizing technical and economic advantages, notably Azerbaijan's geothermal-abundant regions including Lankaran, Khudat, Absheron. research offers comprehensive examination suggested heating system that combines with solar power, objective optimizing efficiency diminishing dependence on fossil fuels. Significant findings include ability hybrid systems to achieve up 85 % thermal reduce consumption by 30 %. For example, Talysh region’s water, operating between 30–64 °C flow rate 14,404 m3/day, can support substantial operations. Geothermal integration Khachmaz sustains consistent 3 hectares space, aligning global benchmarks from nations Iceland, Netherlands, Turkey, have successfully reduced usage carbon emissions. report emphasizes significance utilizing enhance sustainable farming practices. study thorough current resources, recent technological innovations, meticulously organized proposed system, yielding significant insights into future Azerbaijan promoting wider implementation solutions agriculture.

Language: Английский

Citations

0
Research on High-Precision Gas Concentration Inversion for Imaging Fourier Transform Spectroscopy Based on Multi-Scale Feature Attention Model DOI Creative Commons
Jian-Hao Luo,

Zhao Wei,

Fan Ouyang

et al.

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(5), P. 2438 - 2438

Published: Feb. 25, 2025

The accurate monitoring of greenhouse gas (GHG) concentrations is crucial in mitigating global warming. imaging Fourier transform spectrometer (IFTS) an effective tool for measuring GHG concentrations, offering high throughput and a wide spectral measurement range. In order to address the issue inconsistency during detection process target gas, which influenced by external environmental factors, making it difficult achieve high-precision concentration inversion, this paper proposes multi-scale feature attention (MDISE) model. model uses dilated convolution (MD) module retain both local shallow features spectra; introduces one-dimensional Inception (1D Inception) further extract deep features; incorporates channel mechanism (SE) enhance important wavelengths, suppressing redundant interfering information. A system was built laboratory, proposed tested on samples collected two channels short medium-wavelength infrared (SMWIR-IFTS). experimental results show that MDISE reduces root mean square error (RMSE) 79.14%, 76.59%, 69.80%, 81.45%, 82.65%, 74.01%, respectively, compared partial least squares regression (PLSR), support vector (SVR), conventional convolutional neural network (1D-CNN) models. Additionally, achieved average coefficient determination (R2) values 0.997 0.995 intervals channels. demonstrates excellent performance significantly improves accuracy inversion.

Language: Английский

Citations

0
Greenhouse Cooling Systems: A Systematic Review of Research Trends, Challenges, and Recommendations for Improving Sustainability DOI Creative Commons
Fatima Ezzahra Allali, H. Fatnassi,

Hassan Demrati

et al.

Cleaner Engineering and Technology, Journal Year: 2025, Volume and Issue: unknown, P. 100973 - 100973

Published: April 1, 2025

Language: Английский

Citations

0
Analysis of Energy Load according to Design Variables of Building-integrated Rooftop Greenhouse using Building Energy Simulation DOI
Jin-Seok Lee, In-Bok Lee, Da-in Jeong

et al.

Journal of Bio-Environment Control, Journal Year: 2025, Volume and Issue: 34(2), P. 169 - 180

Published: April 30, 2025

Language: Английский

Citations

0
A Sustainable Agri-Photovoltaic Greenhouse for Lettuce Production in Qatar DOI Creative Commons
Yusra Hasan, William David Lubitz

Energies, Journal Year: 2024, Volume and Issue: 17(19), P. 4937 - 4937

Published: Oct. 2, 2024

Qatar identified that food supply security, including self-sufficiency in vegetable production and increasing sustainable renewable energy generation, is important for economic environmental resiliency. Very favorable solar resources suggest opportunities to simultaneously meet this goal by integrating generation production. This study examines the feasibility of developing a agri-photovoltaic (APV) greenhouse design. A comprehensive with included developed year-round operation Lusail, Qatar. The performance system predicted meteorological data MATLAB simulations components. Important design considerations optimizing fixed photovoltaic panels placed on maximum available surface area canopy, while balancing crop insolation needs HVAC systems. Electrical also stored an industrial battery. Results APV technically economically viable it could provide benefits, enhancing promoting energy, contributing

Language: Английский

Citations

3
Runoff Prediction for Hydrological Applications Using an INFO-Optimized Deep Learning Model DOI Open Access
Weisheng Wang,

Yongkang Hao,

Xiaozhen Zheng

et al.

Processes, Journal Year: 2024, Volume and Issue: 12(8), P. 1776 - 1776

Published: Aug. 22, 2024

Runoff prediction is essential in water resource management, environmental protection, and agricultural development. Due to the large randomness, high non-stationarity, low accuracy of nonlinear effects traditional model, this study proposes a runoff model based on improved vector weighted average algorithm (INFO) optimize convolutional neural network (CNN)-bidirectional long short-term memory (Bi-LSTM)-Attention mechanism. First, historical data are analyzed normalized. Secondly, CNN combined with Attention used extract depth local features input weights Bi-LSTM. Then, Bi-LSTM time series feature analysis from both positive negative directions simultaneously. The INFO parameters optimized provide optimal parameter guarantee for CNN-Bi-LSTM-Attention model. Based hydrology station’s level flow data, influence three main models two optimization algorithms compared analyzed. results show that fitting coefficient, R2, proposed 0.948, which 7.91% 3.38% higher than CNN-Bi-LSTM, respectively. R2 vector-weighted 0.993, 0.61% Bayesian (BOA), indicating method adopted paper has more significant forecasting ability can be as reliable tool long-term prediction.

Language: Английский

Citations

0