Environment Development and Sustainability, Journal Year: 2024, Volume and Issue: unknown
Published: Oct. 18, 2024
Language: Английский
Computers & Electrical Engineering, Journal Year: 2024, Volume and Issue: 118, P. 109409 - 109409
Published: June 29, 2024
Artificial intelligence (AI) holds significant promise for advancing natural disaster management through the use of predictive models that analyze extensive datasets, identify patterns, and forecast potential disasters. These facilitate proactive measures such as early warning systems (EWSs), evacuation planning, resource allocation, addressing substantial challenges associated with This study offers a comprehensive exploration trustworthy AI applications in disasters, encompassing management, risk assessment, prediction. research is underpinned by an review reputable sources, including Science Direct (SD), Scopus, IEEE Xplore (IEEE), Web (WoS). Three queries were formulated to retrieve 981 papers from earliest documented scientific production until February 2024. After meticulous screening, deduplication, application inclusion exclusion criteria, 108 studies included quantitative synthesis. provides specific taxonomy disasters explores motivations, challenges, recommendations, limitations recent advancements. It also overview techniques developments using explainable artificial (XAI), data fusion, mining, machine learning (ML), deep (DL), fuzzy logic, multicriteria decision-making (MCDM). systematic contribution addresses seven open issues critical solutions essential insights, laying groundwork various future works trustworthiness AI-based management. Despite benefits, persist In these contexts, this identifies several unused used areas disaster-based theory, collects ML, DL techniques, valuable XAI approach unravel complex relationships dynamics involved utilization fusion processes related Finally, extensively analyzed ethical considerations, bias, consequences AI.
Language: Английский
Citations
48
Remote Sensing, Journal Year: 2025, Volume and Issue: 17(5), P. 774 - 774
Published: Feb. 23, 2025
Wheat (Triticum aestivum L.) is one of the world’s primary food crops, and timely accurate yield prediction essential for ensuring security. There has been a growing use remote sensing, climate data, their combination to estimate yields, but optimal indices time window wheat in arid regions remain unclear. This study was conducted (1) assess performance widely recognized sensing predict at different growth stages, (2) evaluate predictive accuracy machine learning models, (3) determine appropriate period regions, (4) impact parameters on model accuracy. The vegetation indices, due proven effectiveness, used this include Normalized Difference Vegetation Index (NDVI), Enhanced (EVI), Atmospheric Resistance (ARVI). Moreover, four viz. Decision Trees (DTs), Random Forest (RF), Gradient Boosting (GB), Bagging (BTs), were evaluated region. whole divided into three windows: tillering grain filling (December 15–March), stem elongation (January heading (February–March 15). developed Google Earth Engine (GEE), combining data. results showed that RF with ARVI could accurately maturity stages an R2 > 0.75 error less than 10%. stage identified as regions. While delivered best results, GB EVI slightly lower precision still outperformed other models. It concluded multisource data models promising approach
Language: Английский
Citations
1
Paddy and Water Environment, Journal Year: 2024, Volume and Issue: 22(4), P. 503 - 520
Published: June 5, 2024
Language: Английский
Citations
5
Sustainability, Journal Year: 2024, Volume and Issue: 16(18), P. 8125 - 8125
Published: Sept. 18, 2024
Agricultural droughts in South Africa, particularly the Amahlathi Local Municipality (ALM), significantly impact socioeconomic activities, sustainable livelihoods, and ecosystem services, necessitating urgent attention to improved resilience food security. The study assessed interdecadal drought severity duration Amahlathi’s agricultural potential zone from 1989 2019 using various vegetation indicators. Landsat time series data were used analyse land surface temperature (LST), soil-adjusted index (SAVI), normalized difference (NDVI), standardized precipitation (SPI). utilised GIS-based weighted overlay, multiple linear regression models, Pearson’s correlation analysis assess correlations between LST, NDVI, SAVI, SPI response extent. results reveal a consistent negative LST NDVI ALM, with an increase (R2 = 0.9889) temperature. accuracy dry areas increased 55.8% 2019, despite dense high average of 40.12 °C, impacting water availability, land, local ecosystems. shows ALM increasing since 2019. SAVI indicates slight improvement overall health 0.18 0.25 2009, but decrease 0.21 at 12 24 months that severely impacted cover 2014 notable recovery during wet periods 1993, 2000, 2003, 2006, 2008, 2013, possibly due temporary relief. findings can guide provincial monitoring early warning programs, enhancing resilience, productivity, especially farming communities.
Language: Английский
Citations
5
Journal of Electronic Imaging, Journal Year: 2025, Volume and Issue: 34(01)
Published: Jan. 11, 2025
In low-light conditions, object detection algorithms suffer from reduced accuracy due to factors such as noise and insufficient information. Current solutions often involve a two-stage process: first, improving image illumination then performing detection. However, this method has limitations these networks work independently. To address this, we propose parallel algorithm for environments. Our approach simultaneously encodes features using both an enhancement network network. This innovative design allows adapt each other, feature adaptability We enhance adaptive learning efficiency by introducing novel mutual feedback mechanism, which dynamically adjusts the weights of two networks, thereby enhancing network's capacity encode object-related information in conditions. Experiments were conducted on real-world synthetic datasets. On dataset, proposed outperformed original network, achieving improvements 4.76% [email protected], 12.12% [email protected]:0.95, 8.4% F1-score. demonstrated gains 9.67%, 9.75%, 10.6% F1-score, respectively. These experimental results indicate that significantly enhances performance under
Language: Английский
Citations
0
Agricultural Water Management, Journal Year: 2025, Volume and Issue: 309, P. 109347 - 109347
Published: Feb. 2, 2025
Language: Английский
Citations
0
LatIA, Journal Year: 2025, Volume and Issue: 3, P. 322 - 322
Published: May 7, 2025
The convergence of nanotechnology and artificial intelligence (AI) represents a transformative force in agricultural economics, offering innovative solutions to longstanding challenges such as productivity inefficiencies, environmental degradation, unsustainable resource use. This study presents systematic literature review (SLR) aimed at synthesising theoretical frameworks, applications, economic implications associated with these technologies agriculture. A structured search strategy was developed using Boolean operators combine key terms related nanotechnology, AI, machine learning. Comprehensive searches were conducted across six academic databases—Springer, IEEE Xplore, ACM, Science Direct, Wiley, Google Scholar—complemented by manual snowballing techniques. From an initial pool 840 records, 55 studies met the inclusion criteria after rigorous screening eligibility assessment. Findings indicate that enhances nutrient delivery, pest control, crop monitoring through nanosensors nano-fertilisers, while AI facilitates data-driven decision-making, yield prediction, optimisation precision farming. Despite promising results, high investment, technological complexity, limited access for smallholder farmers remain significant. concludes integration can improve efficiency, viability, sustainability. However, targeted investments, capacity-building, interdisciplinary collaboration are essential bridge gap between innovation implementation developing economies.
Language: Английский
Citations
0
Sustainability, Journal Year: 2024, Volume and Issue: 16(23), P. 10399 - 10399
Published: Nov. 27, 2024
The construction sector is increasingly shifting towards sustainable and efficient methodologies, with the industrialized building system (IBS) playing a pivotal role in this transformation. Despite this, adoption of total quality management (TQM) IBS projects faces significant challenges, including lack comprehensive understanding TQM standards resistance to change within industry. This study addresses these gaps by developing framework for implementing projects. objective enhance project sustainability addressing critical issues such as limited stakeholder awareness opposition adoption. Using qualitative methodology rooted phenomenology, explores lived experiences key stakeholders involved projects, managers, professionals, government officials. Data were collected through in-depth interviews capture their perspectives on integration context. findings highlight crucial fostering continuous improvement, enhancing collaboration, ensuring adherence throughout lifecycle. proposed incorporates essential principles process optimization, employee engagement, customer focus, providing structured approach overcoming barriers effective implementation. Furthermore, promotes reducing waste improving energy efficiency offers valuable insights policymakers, industry stakeholders, presenting practical solutions improve construction. Leadership, cultural transformation, improvement are identified factors successful integration, ultimately leading more processes
Language: Английский
Citations
1
Discover Water, Journal Year: 2024, Volume and Issue: 4(1)
Published: Aug. 23, 2024
Groundwater is the most salient and utilitarian water resource for living organisms. However, major parts of Ken River Basin (KRB) in Central India are grappling with overexploitation groundwater resources, primarily due to extensive agricultural activities, raising problems achieving Sustainable Development Goals (SDGs) 2 6. This study focused on delineating potential zones (GPZ) by employing remote sensing GIS-based thematic datasets, complemented application Analytic Hierarchy Process (AHP). The layers consisting geomorphology, precipitation, geology, soil texture, lineament density, slope, LULC, drainage density were considered further weights allocated respect their storing capacity characteristics occurrences develop GPZs. generated classifying overlayed maps into four categories namely, very low, moderate, high. key findings indicated that 13.84%, 62.34%, 23.37%, 45% areas found under high, low GPZs respectively. Furthermore, zonation map was validated 48 boreholes' yield, which revealed a noteworthy 77.08% borewells concurrence predicted zones. Area Under Receiver Operating Characteristic (AUROC) curve showcased commendable 70.1% accuracy using ROC curve. These results highly beneficial formulating sustainable management plans policies, contributing towards attainment targets outlined SDGs 6, particularly regions resembling KRB.
Language: Английский
Citations
0
Environment Development and Sustainability, Journal Year: 2024, Volume and Issue: unknown
Published: Oct. 18, 2024
Language: Английский
Citations
0