Environmental Challenges最新文献

{"title":"Operational losses and environmental flow recovery in a multi-irrigation districts river Basin, evidence from Iran’s arid central plateau","authors":"Farhad Behzadi,&nbsp;Seied Mehdy Hashemy Shahdany","doi":"10.1016/j.envc.2025.101402","DOIUrl":"10.1016/j.envc.2025.101402","url":null,"abstract":"<div><div>This study introduces a systematic technical–environmental appraisal framework that links off-farm operation to environmental flow recovery (EFR) potential in watersheds containing multiple irrigation districts (IDs)The analysis focuses on the surface-water distribution infrastructure within the IDs and, specifically, on off-farm agricultural water management. It considers interconnected open-canal networks, a manual operating system, and the associated standard operating procedures (SOPs). The framework is demonstrated in Iran’s arid central plateau, where six IDs operate in a basin with a long record of environmental water-rights violations linked to agricultural withdrawals. To quantify operational losses, integrated hydraulic–operational models were developed by coupling an integrator–delay hydraulic simulation model with IDs’ SOP logic. The models were calibrated and verified for all six IDs. The technical assessment indicates that daily water losses caused by operational failures and inefficiencies vary markedly across operating conditions. Under normal to severe shortage scenarios, these losses account for 6.5–17.3% and 21.5–31.1% of the supplied surface water, respectively. To estimate the EFR recovery potential, the study applied an flow-duration-curve (FDC)-shifting approach together with the Global Environmental Flow Calculator (GEFC). Under the best-case scenario, 61 MCM yr⁻¹ can be recovered from operational losses and returned to the river, which corresponds to 45.16% of the flow deficit required to satisfy class F. Even under the most severe shortage scenario, 13 MCM yr⁻¹ (9.63% of the class F deficit) remains recoverable. Overall, the proposed framework is transferable to similar multi-ID watersheds and provides technical evidence to support licensing decisions for off-farm system automation, enabling basin authorities, licensing agencies, and irrigation-district managers to audit operational losses, define diversion-reduction targets at diversion dams, and operationalize compliance monitoring for environmental-flow releases.</div></div>","PeriodicalId":34794,"journal":{"name":"Environmental Challenges","volume":"22 ","pages":"Article 101402"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146078078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A remediation approach for the petroleum industry using optimized biodegradable single-use SDS-surfactant in the treatment of soil contaminated with domestic-purpose-kerosene","authors":"Vincent Oshevwiyo Akpoveta ,&nbsp;Ese Queen Umudi ,&nbsp;Bright Ogbolu ,&nbsp;Mabel Ajevwaye Afure ,&nbsp;John Arigbede ,&nbsp;John Opeyemi Thomas","doi":"10.1016/j.envc.2025.101388","DOIUrl":"10.1016/j.envc.2025.101388","url":null,"abstract":"<div><div>Surfactants are known to aid in removing organic contaminants from soil. However, selecting a suitable surfactant for mitigating hydrocarbon pollution is an important environmental consideration during remediation. Previous studies report surfactant mixtures with a remediation focus on petroleum products, other than kerosene. This study focuses on applying an optimized biodegradable single-use sodium dodecyl sulphate (SDS) surfactant in treating domestic-purpose-kerosene (DPK)-contaminated soil. Soil quality indicators (pH, conductivity, total nitrogen, total phosphorus, organic carbon, organic matter, soil texture, and heavy metals), total petroleum hydrocarbon (TPH) levels (as kerosene), and optimization protocols were determined using standard methods. Simulating soil with 10 % DPK increased TPH by 22,800.8 % (from 8.64 ppm to 1978.63 ppm) and affected soil quality indicators, except for heavy metals and soil texture. The optimization protocol yielded conditions (optimal SDS concentration of 2 % for soil treatment at pH 4.5, under ambient temperature) that can guide practical field-scale soil remediation strategies. TPH was significantly reduced, with a remediation rate of 84.65 % after 8 h of treatment. Most of the affected soil properties improved after treatment. The kinetics of the treatment process followed Pseudo-First order, with a rate constant of 0.215 h-1 and a calculated half-life of 3 h, 13 min, and 12 s. The associated advantages of this technique, especially in terms of efficiency and versatility, make it ideal for real field challenges. The observed remediation effectiveness from using SDS alone provides a viable option as a single-use surfactant for kerosene decontamination from soil, without the need for combination with other surfactants or remediation techniques, thereby reducing dependence on more expensive and complex multi-step techniques.</div></div>","PeriodicalId":34794,"journal":{"name":"Environmental Challenges","volume":"22 ","pages":"Article 101388"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145798444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dye removal from wastewater using ferrihydrite-modified sugarcane bagasse and biochar: Adsorption performance and modeling analysis","authors":"Nipa Das ,&nbsp;Saikat Barua ,&nbsp;Md. Abul Kashem ,&nbsp;Mohammad Moniruzzaman ,&nbsp;Muhammad Shahriar Bashar ,&nbsp;Md. Shoffikul Islam","doi":"10.1016/j.envc.2025.101390","DOIUrl":"10.1016/j.envc.2025.101390","url":null,"abstract":"<div><div>Cationic and anionic dyes in wastewater pose significant environmental risks due to their toxicity, persistence, and mobility. To address this issue, sugarcane bagasse (SB) and its biochar (SBB) were treated with ferrihydrite (Fh) to produce cost-effective and durable adsorbents for the simultaneous removal of methylene blue (MB, cationic) and methyl orange (MO, anionic). In single-dye systems, the ferrihydrite-biochar composite (2Fh-SBB) achieved peak Langmuir adsorption capacities of 141.75 mg g⁻¹ for MB and 138.25 mg g⁻¹ for MO, outperforming SB, SBB, Fh, and 2Fh-SB. The Freundlich model further suggested heterogeneous adsorption behavior compatible with the composite's mixed carbon-ferrihydrite surface. The kinetic data were well characterized by the pseudo-second-order model (R² = 0.97–0.99), suggesting the participation of surface interactions; yet, kinetics alone cannot differentiate between physisorption and chemisorption. Temperature-dependent thermodynamic analyses (ΔG°, ΔH°, ΔS°) are necessary for conclusive mechanistic validation. Statistical diagnostics validated the reliability of the isotherm and kinetic parameters. MB adsorption favored alkaline conditions, while MO adsorption was higher at acidic pH, reflecting electrostatic influences relative to surface charge and pHPZC. In binary systems, MB adsorption was enhanced by MO, indicating partial synergistic effects associated with charge heterogeneity and improved Fh dispersion. Characterization tests (BET, zeta potential, FTIR, SEM-EDS) suggested that MB interacted with both carbon and Fh domains via electrostatic and π-π interactions, while MO adsorption involves Fe-O surface interactions. The substantial and largely stable adsorption fractions highlight the effectiveness of ferrihydrite modification in pollutant stabilization. Overall, 2Fh-SBB demonstrates strong potential as a low-cost, robust adsorbent for multi-dye wastewater treatment while promoting the valorization of agricultural waste.</div></div>","PeriodicalId":34794,"journal":{"name":"Environmental Challenges","volume":"22 ","pages":"Article 101390"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145749833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advancing irrigated area mapping using machine learning and deep learning approaches: The case of Awash Valley, Ethiopia","authors":"Berhan Gessesse ,&nbsp;Gebeyehu Abebe ,&nbsp;Gezahagn Woldu ,&nbsp;Zerihun Chere","doi":"10.1016/j.envc.2026.101408","DOIUrl":"10.1016/j.envc.2026.101408","url":null,"abstract":"<div><div>Accurate and timely data on irrigated cropland in the arid lowlands of Ethiopia are required to strengthen national food security resilience. However, conventional mapping methods remain inconsistent to provide accurate information about irrigated farming practices. This study addresses these gaps by evaluating multisource Earth Observation (EO) data using advanced machine learning (such as SVM, RF) and state-of-the-art deep learning (ResUNet). Using Sentinel-2 Level 2(S2A) imagery, we designed three classification scenarios: i) six spectral bands; ii) spectral bands plus three vegetation indices, including the Enhanced Vegetation Index (EVI), Normalized Difference Vegetation Index (NDVI), and Land Surface Water Index (LSWI); and iii) an expanded feature set incorporating spectral texture metrics such as variance, contrast and dissimilarity. These models provide a robust framework for quantifying irrigated areas in the Awash basin, overcoming conventional data limitations. Model outputs were rigorously validated using ground reference data. This study evaluates the transformative potential of the ResUNet deep learning architecture for precise irrigation and land-use mapping in Ethiopia’s heterogeneous Awash basin landscape. By integrating multispectral bands, vegetation indices and spectral features, ResUNet achieved a superior Overall Accuracy of 84.13% and Kappa of 0.83, significantly outperforming SVM (67.54%) and Random Forest (82.33%). The model’s residual learning framework proved essential for capturing complex spatial-spectral hierarchies in semi-arid zones, achieving a peak F1-score of 0.89 for irrigated area detection. Beyond technical performance, this automated approach provides essential monitoring capabilities to support water resource management, drought early-warning systems, and food security estimation for smallholder farmers.</div></div>","PeriodicalId":34794,"journal":{"name":"Environmental Challenges","volume":"22 ","pages":"Article 101408"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146038092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing machine learning-based gully erosion susceptibility modeling using a prediction-oriented spatial cross-validation framework","authors":"Eyasu Mekonnen ,&nbsp;Asfaw Kebede ,&nbsp;Samuel Feyissa ,&nbsp;Solomon Asfaw ,&nbsp;Lemma Zemedu","doi":"10.1016/j.envc.2026.101418","DOIUrl":"10.1016/j.envc.2026.101418","url":null,"abstract":"<div><div>Prediction where gullies are likely to form is essential for sustainable land management in fragile ecosystem. Machine learning (ML) has advanced gully erosion susceptibility modeling by capturing complex, non-linear geospatial relationships. However, most ML applications often rely on random cross-validation, a non-spatial approach that inflates model performance metrics and limits predictive generalization. This study aims to optimize ML-based gully erosion susceptibility modeling in Upper Awash River Basin using a spatially explicit k-fold Nearest Neighbor Distance Matching (kNNDM) cross-validation framework. Five ML algorithms: Random Forest, Gradient Boosting Machine, Naïve Bayes (NB), Artificial Neural Network (ANN), and Support Vector Machine (SVM) were trained using 584 georeferenced gully and non-gully points derived from field surveys and high-resolution imagery. Both spatial and random partitioning tested with training (80%) and validation (20%) sets. Feature selection identified land use/land cover as the most influential gully-conditioning factor. Models trained with spatial cross-validation produced more realistic and unbiased performance estimates compared to inflated metrics from random partitioning. Among all algorithms, SVM achieved the best balance of predictive accuracy and generalizability (Accuracy = 0.788, ROC-AUC = 0.831, F1 = 0.783), followed by ANN (Accuracy = 0.735, ROC-AUC = 0.844 and F1 score = 0.747), while NB performed low due to its simplistic assumptions of feature independence in such complex geomorphological processes. The resulting susceptibility map delineates gully-prone zones ranging from low to very high risk, within Areas of Applicability. Cultivated and bare landscapes exhibited the highest susceptibility, highlighting the need for targeted, spatially informed intervention. The suitability of kNNDM framework demonstrates a reliable spatial validation approach for gully erosion modeling in data-scarce regions, enhancing predictive reliability and supporting evidence-based land management and conservation planning.</div></div>","PeriodicalId":34794,"journal":{"name":"Environmental Challenges","volume":"22 ","pages":"Article 101418"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146188497","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Microplastic fragments in sand alleviate the negative effects of heavy metals on plants","authors":"Elizaveta Shcherbinina ,&nbsp;Marie E Muehe ,&nbsp;Sören Drabesch ,&nbsp;Katja Tielbörger ,&nbsp;Sara Tomiolo","doi":"10.1016/j.envc.2026.101421","DOIUrl":"10.1016/j.envc.2026.101421","url":null,"abstract":"<div><div>We investigated the effects of microplastic (MP) and cadmium (Cd) on the performance of plant species with distinct Cd tolerance levels. We hypothesized that MP may affect Cd bioavailability via direct interactions or indirectly modifying pH, water content and bioavailability of other elements in the substrate.</div><div><em>Arabidopsis thaliana</em> (non-hyperaccumulator) and <em>Arabidopsis halleri</em> (metal-hyperaccumulator) were exposed to different concentrations of Cd and MP. Plant biomass, Cd bioavailability in the substrate, Cd and other elements’ uptake by plants were assessed, and substrate’s properties monitored.</div><div>Biomass of <em>A. halleri</em> weakly responded to MP and Cd. <em>A. thaliana</em> biomass decreased when exposed to either Cd or MP and increased when exposed to both stressors. In both species, high MP concentrations in the substrate promoted higher Cd bioavailability, but reduced Cd uptake by plants. Cd bioavailability was not explained by substrate’s pH or water content. However, variation in other elements uptake in the two species was strongly correlated with Cd and weakly with MP concentrations.</div><div>The findings of this study suggest a direct interaction between MP and Cd mediating shifts in Cd bioavailability and Cd uptake in plants as well as indirect effects mediated by element uptake. This work provides insights on the complex interplay between MP and Cd.</div></div>","PeriodicalId":34794,"journal":{"name":"Environmental Challenges","volume":"22 ","pages":"Article 101421"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146188484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advancing postharvest storage management using sensors and smart technologies: A national and global perspective","authors":"Awais Ahmad ,&nbsp;Fazal Jalal ,&nbsp;Shah Fahad ,&nbsp;Nazia Tahir ,&nbsp;Aqib Iqbal ,&nbsp;Rukhsar Bakhtaj ,&nbsp;Sarir Ahmad ,&nbsp;Zafar Hayat Khan ,&nbsp;Badshah Islam ,&nbsp;Mahmood Hemat ,&nbsp;Tanzeel Ur Rahman ,&nbsp;Shah Saud ,&nbsp;Taufiq Nawaz","doi":"10.1016/j.envc.2025.101379","DOIUrl":"10.1016/j.envc.2025.101379","url":null,"abstract":"<div><div>The transformation of crop yield storage management through sensor technologies is the most promising solution, addressing the critical issue of post-harvest losses that threaten global food security. The present review explains various sensor-based systems in monitoring and controlling environmental factors such as temperature, humidity and gas emissions to maintain crop quality and prevent spoilage. This review followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analysis for Scoping Reviews) guidelines to ensure transparency, rigor and reproducibility in literature identification, screening and synthesis. The review discusses sensor applications across various crop types that range wide from cereals and pulses to perishable fruits and high-value crops, emphasizing customized solutions targeting specific storage requirements. On a regional basis, disparities in technological advancement are evident, with high-tech automated systems being the predominantly concentrated in developed countries, whereas those that favor innovation with sensor solutions that are cheap and scalable, while developing countries are characterized by infrastructural constrains and a focus on affordable, scalable innovations. Pakistan’s early initiatives in sensor-based storage management illustrate how much technologies can enhance agricultural resilience in similar developing context. The initial disposition of Pakistan toward sensor-centered storage management serves as an emblem of how such technology can promote agricultural resilience in settings of comparable nature. Economic analysis indicates a favorable cost-benefit ratio for sensors deployment, hinged upon a reduction in post-harvest losses, energy efficiency in storage, and socioeconomic upliftment of smallholder farmers. Nevertheless, challenges such as high initial investment, skill gaps, sensor durability, connectivity challenges, and policy hurdles remain acute. The future is one where AI powered smart storage systems, nanotechnology-based sensors, and synergized digital ecosystems will offer precision, automation, and sustainability. This requires joint efforts between governments, the private sector, and international agencies to increase the scale of innovations and build capacity. Overall, sensors technologies are revolutionizing sustainable, technology-enabled agricultural storages systems that preserve food security, promote efficient resource use and improve livelihood worldwide.</div></div>","PeriodicalId":34794,"journal":{"name":"Environmental Challenges","volume":"22 ","pages":"Article 101379"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145749829","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning-enhanced air quality forecasting and trend analysis: A five-year comprehensive assessment of PM2.5 concentrations in Bangkok, Thailand","authors":"Jeevan Bhatta ,&nbsp;Shiva Raj Acharya ,&nbsp;Kwang Mo Yang","doi":"10.1016/j.envc.2026.101442","DOIUrl":"10.1016/j.envc.2026.101442","url":null,"abstract":"<div><div>Air pollution forecasting is crucial for protecting public health in rapidly urbanizing Asian megacities; however, comprehensive comparative studies of advanced machine learning approaches are limited in Southeast Asian urban environments. This study developed and systematically compared three state-of-the-art machine learning algorithms for operational PM_2.5 forecasting in Bangkok, Thailand, using comprehensive monitoring data from 2020 to 2024. Daily PM_2.5 concentrations and meteorological variables, including temperature, rainfall, wind speed, atmospheric pressure, and relative humidity, were collected from 12 monitoring stations across Bangkok. Three machine learning approaches were implemented and compared: Random Forest (RF), Gradient Boosting (GB), and Long Short-Term Memory (LSTM) neural networks. Advanced feature engineering incorporated temporal lags, moving averages, and cyclical encoding to capture seasonal and temporal dependencies. The dataset comprised 1827 daily observations across all variables. PM_2.5 concentrations exhibited pronounced seasonal variations, with a mean of 21.89 ± 8.71 μg/m³, ranging from winter highs of 29.78 ± 7.88 μg/m³ to rainy-season lows of 14.58 ± 3.16 μg/m³. Strong positive correlations were observed between PM_2.5 and atmospheric pressure (r = 0.473), while negative correlations were found with rainfall (r = -0.260) and relative humidity (r = -0.237). Gradient Boosting demonstrated superior predictive performance, with an RMSE of 2.17 μg/m³ and an R² of 0.935 on an independent external validation dataset comprising 365 days of 2024 data, withheld entirely from model development, confirming genuine generalization to unseen future data. Random Forest achieved RMSE = 3.34 μg/m³ and R² = 0.845 on the same external validation set. To address overfitting identified in preliminary analyses (training R² = 0.964), hyperparameter regularization was substantially strengthened, yielding R² degradation of only 3.9% (Gradient Boosting) and 5.6% (Random Forest) from training to external validation. Feature importance analysis revealed that PM_2.5 temporal features dominated the predictions, with the 3-day moving average achieving the highest importance in Random Forest (42.17%) and Gradient Boosting (60.41%). Short-term forecasting performance (1–7 days) met operational requirements for early warning systems, but performance degraded significantly beyond 14 days. The validated Gradient Boosting framework provides immediate applicability for environmental agencies across Southeast Asian urban centers, supporting evidence-based air quality management and public health protection in rapidly developing megacities.</div></div>","PeriodicalId":34794,"journal":{"name":"Environmental Challenges","volume":"22 ","pages":"Article 101442"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147395634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Achieving zero hunger: A global policy lens on food security drivers and income group disparities","authors":"Nirmani Pulle ,&nbsp;Prasad Sampath ,&nbsp;Sarah Perera ,&nbsp;Dinuli Wijayaweera ,&nbsp;Ruwan Jayathilaka","doi":"10.1016/j.envc.2026.101409","DOIUrl":"10.1016/j.envc.2026.101409","url":null,"abstract":"<div><div>Many countries struggle to meet their daily dietary requirements despite numerous attempts to address the existing demand. Consequently, this study collectively analyses the impact of urbanisation, renewable energy, greenhouse gas emissions, population growth, gross domestic product per capita and agricultural land on food production relying on Sen’s Entitlement Theory, thus providing insights to resolve the long-standing issue of food insecurity, and support the achievement of the Sustainable Development Goals. The study utilises a stepwise panel ordered Probit model on 146 countries, for the years 1993 to 2023. It further categorises the food production index into three categories of food security as; low, moderate and high, thereby enabling discussion of the likelihood of a country falling into one of the aforementioned food security categories over the years. Urbanisation, agricultural land, and the dummy variables introduced to represent the income groups have been identified to have a significant and favourable relationship with the food production index. In contrast, the greenhouse gas emissions and renewable energy variables have a significantly inverse impact on the food production index. This makes a unique contribution to the existing body of literature, especially by comparing odds over the years, across different food secure categories, countries, and their specific income levels. This study enables policymakers to gain a comprehensive historical perspective on each case. This study further promotes the Sustainable Development Goals, highlighting areas where these goals have been negatively impacted. Additionally, the study discusses optimised investment allocations, agricultural research and development, agricultural technology, climate resilient farming, and sustainable urbanisation planning as solutions for extreme cases.</div></div>","PeriodicalId":34794,"journal":{"name":"Environmental Challenges","volume":"22 ","pages":"Article 101409"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146038087","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI-driven biomass discrimination of palm fronds using low-cost vision sensors for sustainable waste valorization","authors":"Ramayanty Bulan ,&nbsp;Darwin ,&nbsp;Devianti ,&nbsp;Agustami Sitorus ,&nbsp;Hasanuddin","doi":"10.1016/j.envc.2025.101397","DOIUrl":"10.1016/j.envc.2025.101397","url":null,"abstract":"<div><div>The development of agricultural machinery for palm trees still faces challenges due to differences in the physical and mechanical properties of fronds and leaves between species. Shredding machines that operate without sensors have difficulty adjusting rotational speed and cutting angle, resulting in decreased performance when faced with variations in raw materials. Therefore, the objective of this study is to classify three types of palm fronds and leaves, including <em>Areca catechu</em> L. (AR), <em>Cocos nucifera</em> (CN), and <em>Elaeis guineensis</em> Jacq. (EG), using a low-cost camera with a resolution of 1920 × 1080 pixels, combined with ensemble machine learning. Samples were prepared under fresh, incubated, and dried conditions, comprising a total of 810 fronds and 972 leaves. Three feature extraction methods were applied, including RGB, Oriented FAST and Rotated BRIEF (ORB), and Lab color space, which were then analyzed using two machine learning ensemble algorithms, including gradient boosting for classification (GBC) and histogram-based gradient boosting classification tree (HGBC). The combination of ORB with HGBC achieved the highest accuracy for fronds (79.6%), while Lab with HGBC was superior for leaves (84.6%). The Lab is the most consistent feature, while ORB is clear for fronds structure. This classification system has the potential to be used as a smart sensor integrated into palm shredding machines, enabling automated operation control and increasing biomass processing efficiency.</div></div>","PeriodicalId":34794,"journal":{"name":"Environmental Challenges","volume":"22 ","pages":"Article 101397"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145939034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}