Environmental Challenges最新文献_第2页

Enhancing machine learning-based gully erosion susceptibility modeling using a prediction-oriented spatial cross-validation framework 使用面向预测的空间交叉验证框架增强基于机器学习的沟道侵蚀敏感性建模

Q2 Environmental Science

Environmental Challenges

Pub Date : 2026-01-26 DOI: 10.1016/j.envc.2026.101418

Eyasu Mekonnen , Asfaw Kebede , Samuel Feyissa , Solomon Asfaw , Lemma Zemedu

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.

对脆弱生态系统中可能形成沟壑的区域进行预测是土地可持续管理的重要内容。机器学习（ML）通过捕获复杂的非线性地理空间关系，提高了沟壑侵蚀敏感性建模。然而，大多数ML应用程序通常依赖于随机交叉验证，这是一种非空间方法，会夸大模型性能指标并限制预测泛化。本研究旨在利用空间显式k-fold最近邻距离匹配（kNNDM）交叉验证框架，优化基于ml的上阿瓦什河流域沟道侵蚀敏感性模型。5种机器学习算法：随机森林（Random Forest）、梯度增强机（Gradient Boosting Machine）、Naïve贝叶斯（NB）、人工神经网络（ANN）和支持向量机（SVM），使用584个基于地理参考的沟壑和非沟壑点（来源于野外调查和高分辨率图像）进行训练。空间和随机分区都用训练集（80%）和验证集（20%）进行了测试。特征选择表明土地利用/土地覆被是影响最大的沟壑区调节因子。与来自随机分区的夸大指标相比，使用空间交叉验证训练的模型产生了更现实和无偏的性能估计。在所有算法中，SVM在预测精度和可泛化性方面达到了最好的平衡（准确率= 0.788,ROC-AUC = 0.831, F1 = 0.783）， ANN次之（准确率= 0.735,ROC-AUC = 0.844， F1得分= 0.747），NB算法由于在如此复杂的地貌过程中对特征独立性的假设过于简单，表现较差。由此产生的易感性图描绘了适用区域内从低到极高风险的易沟壑区。开垦和裸露的景观表现出最高的易感性，强调需要有针对性的、空间知情的干预。kNNDM框架的适用性为数据稀缺地区的沟沟侵蚀建模提供了可靠的空间验证方法，提高了预测的可靠性，并为基于证据的土地管理和保护规划提供了支持。

{"title":"Enhancing machine learning-based gully erosion susceptibility modeling using a prediction-oriented spatial cross-validation framework","authors":"Eyasu Mekonnen , Asfaw Kebede , Samuel Feyissa , Solomon Asfaw , 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":"2026-01-26","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}

引用次数: 0

Spatially divergent impacts of global nutrient emission scenarios on freshwater community intactness 全球营养物排放情景对淡水群落完整性的空间差异影响

Q2 Environmental Science

Environmental Challenges

Pub Date : 2026-01-24 DOI: 10.1016/j.envc.2026.101417

Floris K. Neijnens , Selwyn Hoeks , Hadassa Moreira , Koen J.J. Kuipers , Arthur H.W. Beusen , Gertjan W. Geerling , Mark A.J. Huijbregts , Aafke M. Schipper

Eutrophication presents a persistent challenge to biodiversity conservation in freshwater systems worldwide. Yet, a global assessment of potential future nutrient-induced losses of freshwater biodiversity integrity is currently lacking. Here, we evaluated the effects of freshwater nitrogen (N) and phosphorus (P) concentrations on freshwater community intactness for three potential future development scenarios from the shared socio-economic pathway (SSP) framework: the sustainability scenario (SSP1), the regional rivalry scenario (SSP3), and the fossil-fuelled development scenario (SSP5). We first derived novel relationships between freshwater invertebrate and macrophyte community intactness (quantified with the mean species abundance (MSA) indicator) and nutrient concentrations, based on a recently published database of N and P addition experiments. We then used these relationships to estimate changes in MSA values from 2010 to 2070 based on global nutrient concentration maps for the different SSP scenarios. All three scenarios resulted in further declines in global mean MSA, with the smallest declines for the sustainability scenario and the largest for the regional rivalry scenario. Future declines in community intactness were most prominent in African river basins (Nile, Congo), whereas we observed future increases in community intactness in river basins in Europe (Rhine, Dnieper), North America (Mississippi), and Eastern Asia (Ganges, Yangtze), particularly for the sustainability scenario. Our results indicate that halting further freshwater biodiversity decline requires increased and concerted scientific and societal efforts to reduce eutrophication, in particular in river basins where biodiversity intactness is currently high yet large future decline are projected.

富营养化是全球淡水系统生物多样性保护面临的一个持续挑战。然而，目前缺乏对未来可能由营养引起的淡水生物多样性完整性损失的全球评估。本文基于共享社会经济路径（SSP）框架，在可持续性情景（SSP1）、区域竞争情景（SSP3）和化石燃料发展情景（SSP5）三种潜在的未来发展情景下，评估了淡水氮(N)和磷(P)浓度对淡水群落完整性的影响。我们首先基于最近发表的N和P添加实验数据库，推导出淡水无脊椎动物和大型植物群落完整性（用平均物种丰度（MSA）指标量化）与营养浓度之间的新关系。然后，我们根据不同SSP情景下的全球养分浓度图，利用这些关系估计了2010年至2070年MSA值的变化。所有三种情景均导致全球平均MSA进一步下降，其中可持续性情景下降幅度最小，区域竞争情景下降幅度最大。未来群落完整性的下降在非洲流域（尼罗河、刚果）最为显著，而我们观察到未来群落完整性在欧洲流域（莱茵河、第聂伯河）、北美流域（密西西比河）和东亚流域（恒河、长江）的增加，特别是在可持续性情景中。我们的研究结果表明，阻止淡水生物多样性的进一步下降需要加大和协调的科学和社会努力来减少富营养化，特别是在目前生物多样性完整性高但预计未来会大幅下降的河流流域。

{"title":"Spatially divergent impacts of global nutrient emission scenarios on freshwater community intactness","authors":"Floris K. Neijnens , Selwyn Hoeks , Hadassa Moreira , Koen J.J. Kuipers , Arthur H.W. Beusen , Gertjan W. Geerling , Mark A.J. Huijbregts , Aafke M. Schipper","doi":"10.1016/j.envc.2026.101417","DOIUrl":"10.1016/j.envc.2026.101417","url":null,"abstract":"<div><div>Eutrophication presents a persistent challenge to biodiversity conservation in freshwater systems worldwide. Yet, a global assessment of potential future nutrient-induced losses of freshwater biodiversity integrity is currently lacking. Here, we evaluated the effects of freshwater nitrogen (N) and phosphorus (P) concentrations on freshwater community intactness for three potential future development scenarios from the shared socio-economic pathway (SSP) framework: the sustainability scenario (SSP1), the regional rivalry scenario (SSP3), and the fossil-fuelled development scenario (SSP5). We first derived novel relationships between freshwater invertebrate and macrophyte community intactness (quantified with the mean species abundance (MSA) indicator) and nutrient concentrations, based on a recently published database of N and P addition experiments. We then used these relationships to estimate changes in MSA values from 2010 to 2070 based on global nutrient concentration maps for the different SSP scenarios. All three scenarios resulted in further declines in global mean MSA, with the smallest declines for the sustainability scenario and the largest for the regional rivalry scenario. Future declines in community intactness were most prominent in African river basins (Nile, Congo), whereas we observed future increases in community intactness in river basins in Europe (Rhine, Dnieper), North America (Mississippi), and Eastern Asia (Ganges, Yangtze), particularly for the sustainability scenario. Our results indicate that halting further freshwater biodiversity decline requires increased and concerted scientific and societal efforts to reduce eutrophication, in particular in river basins where biodiversity intactness is currently high yet large future decline are projected.</div></div>","PeriodicalId":34794,"journal":{"name":"Environmental Challenges","volume":"22 ","pages":"Article 101417"},"PeriodicalIF":0.0,"publicationDate":"2026-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077920","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}

引用次数: 0

Multi-index evaluation of surface water quality at the transboundary section of the Mekong River: A case study of Nakhon Phanom Province, Thailand 湄公河跨界河段地表水水质多指标评价——以泰国那空巴侬省为例

Q2 Environmental Science

Environmental Challenges

Pub Date : 2026-01-23 DOI: 10.1016/j.envc.2026.101414

Torpong Kreetachat , Saksit Imman , Nopparat Suriyachai , Nathiya Kreetachat , Sukanya Hongthong , Kowit Suwannahong , Panarat Phadee , Athicha Janthakhot , Surachai Wongcharee

A seasonal, multi-index examination of surface water quality was performed for the Mekong River at the Thailand-Lao transboundary section in Nakhon Phanom Province, utilizing six internationally recognized Water Quality Indices such as MRC-WQI_al, PCD-WQI, NSF-WQI, CCME-WQI, BIS-WQI, and EU-WQI. The monitoring period showed that the Mekong River always had good oxygen levels (DO = 7.48–8.77 mg/L), which shows that it has a strong ability to clean itself. However, pronounced nutrient amplification during the dry season became the primary ecological control, with ammonium levels rising from 0.03 to 0.04 to 0.27–0.39 mg/L, nitrate levels from 0.23 to 0.32 to 1.86–1.95 mg/L, and total phosphorus levels from 0.04 to 0.06 to 0.43–0.48 mg/L, surpassing eutrophication thresholds by nearly threefold. Microbial contamination exhibited an inverse seasonal trend, with total coliforms reaching their zenith in the wet season (1.69–1.90 × 10⁴ MPN 100 mL⁻¹) because of storm runoff and diffuse fecal loading, subsequently experiencing a 5–6-fold reduction in the dry season. The assessment of heavy metals revealed that most elements had low concentrations. However, cadmium consistently exceeded international safety limits, resulting in hazard quotients as high as 6.67 and dominating the overall ecological risk index. There was a big difference between the WQI frameworks. Ecological indices (MRC-WQIal and CCME-WQI) showed a clear change from good to very good quality in the wet season to bad to marginal quality in the dry season. On the other hand, general-use indices (PCD-WQI, NSF-WQI, BIS-WQI) still rated the river as good to very good, showing that single-index interpretation can hide a lot of risk. The Mekong River has two types of seasonal risks right now: wet-season microbial contamination and dry-season phosphorus-driven eutrophication. There is also a constant risk of cadmium. These results show reliable transboundary river management and early warning of ecological degradation in the Lower Mekong Basin, which need integrated, multi-index, seasonally resolved frameworks.

利用mrc - wqi、PCD-WQI、NSF-WQI、CCME-WQI、BIS-WQI和EU-WQI等6个国际公认的水质指数，对泰国-老挝湄公河那空Phanom省跨界河段的地表水水质进行了季节性多指标检测。监测期内，湄公河的氧含量一直处于良好状态（DO = 7.48 ~ 8.77 mg/L），表明其具有较强的自我清洁能力。然而，旱季养分显著扩增成为主要的生态控制因素，铵态氮含量从0.03 ~ 0.04上升到0.27 ~ 0.39 mg/L，硝态氮含量从0.23 ~ 0.32上升到1.86 ~ 1.95 mg/L，总磷含量从0.04 ~ 0.06上升到0.43 ~ 0.48 mg/L，超过富营养化阈值近3倍。微生物污染呈现出逆季节趋势，由于暴雨径流和弥漫的粪便负荷，大肠菌群总数在雨季达到顶峰（1.69-1.90 × 10⁴MPN 100 mL⁻¹），随后在旱季经历了5 - 6倍的减少。对重金属的评估显示，大多数元素的浓度较低。但镉持续超过国际安全限值，危害系数高达6.67，在整体生态风险指数中占主导地位。WQI框架之间有很大的不同。生态指标（mrc - wqal和CCME-WQI）在丰水季表现出从优良到极好到差到边缘的变化趋势。另一方面，通用指标（PCD-WQI、NSF-WQI、BIS-WQI）仍将河流评价为“好”至“非常好”，表明单一指标解释可能隐藏了很多风险。湄公河目前有两种季节性风险：雨季微生物污染和旱季磷驱动的富营养化。镉的风险也一直存在。这些结果表明，湄公河下游跨境河流管理和生态退化预警是可靠的，这需要综合的、多指标的、季节性解决的框架。

{"title":"Multi-index evaluation of surface water quality at the transboundary section of the Mekong River: A case study of Nakhon Phanom Province, Thailand","authors":"Torpong Kreetachat , Saksit Imman , Nopparat Suriyachai , Nathiya Kreetachat , Sukanya Hongthong , Kowit Suwannahong , Panarat Phadee , Athicha Janthakhot , Surachai Wongcharee","doi":"10.1016/j.envc.2026.101414","DOIUrl":"10.1016/j.envc.2026.101414","url":null,"abstract":"<div><div>A seasonal, multi-index examination of surface water quality was performed for the Mekong River at the Thailand-Lao transboundary section in Nakhon Phanom Province, utilizing six internationally recognized Water Quality Indices such as MRC-WQI<sub>al</sub>, PCD-WQI, NSF-WQI, CCME-WQI, BIS-WQI, and EU-WQI. The monitoring period showed that the Mekong River always had good oxygen levels (DO = 7.48–8.77 mg/L), which shows that it has a strong ability to clean itself. However, pronounced nutrient amplification during the dry season became the primary ecological control, with ammonium levels rising from 0.03 to 0.04 to 0.27–0.39 mg/L, nitrate levels from 0.23 to 0.32 to 1.86–1.95 mg/L, and total phosphorus levels from 0.04 to 0.06 to 0.43–0.48 mg/L, surpassing eutrophication thresholds by nearly threefold. Microbial contamination exhibited an inverse seasonal trend, with total coliforms reaching their zenith in the wet season (1.69–1.90 × 10⁴ MPN 100 mL⁻¹) because of storm runoff and diffuse fecal loading, subsequently experiencing a 5–6-fold reduction in the dry season. The assessment of heavy metals revealed that most elements had low concentrations. However, cadmium consistently exceeded international safety limits, resulting in hazard quotients as high as 6.67 and dominating the overall ecological risk index. There was a big difference between the WQI frameworks. Ecological indices (MRC-WQIal and CCME-WQI) showed a clear change from good to very good quality in the wet season to bad to marginal quality in the dry season. On the other hand, general-use indices (PCD-WQI, NSF-WQI, BIS-WQI) still rated the river as good to very good, showing that single-index interpretation can hide a lot of risk. The Mekong River has two types of seasonal risks right now: wet-season microbial contamination and dry-season phosphorus-driven eutrophication. There is also a constant risk of cadmium. These results show reliable transboundary river management and early warning of ecological degradation in the Lower Mekong Basin, which need integrated, multi-index, seasonally resolved frameworks.</div></div>","PeriodicalId":34794,"journal":{"name":"Environmental Challenges","volume":"22 ","pages":"Article 101414"},"PeriodicalIF":0.0,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077919","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}

引用次数: 0

Drinking water quality, environmental health risk assessment, and household perceptions of preventive capacity in the Ciliwung Watershed, Indonesia 印度尼西亚Ciliwung流域的饮用水质量、环境健康风险评估和家庭对预防能力的认识

Q2 Environmental Science

Environmental Challenges

Pub Date : 2026-01-23 DOI: 10.1016/j.envc.2026.101416

Fitri Kurniasari , Bambang Wispriyono , Sifa Fauzia , Ghina Labibah , Alfian Fauzi Firdaus , Masashi Kato

Limited access to piped water infrastructure has made drinking water quality a critical public health concern in many developing countries, including Indonesia. In densely populated urban areas of Greater Jakarta, households within the Ciliwung Watershed continue to rely heavily on groundwater sources that are vulnerable to chemical and microbiological contamination. This study comprehensively assessed drinking water quality, performed a screening-level environmental health risk assessment, and evaluated household awareness and preventive capacity in the Ciliwung Watershed. Water samples were collected from four locations representing upstream, midstream, and downstream sections of the watershed and analyzed for chemical parameters (Mn, NO3-, Fe, and Zn) and microbiological indicators (total coliforms). A screening-level environmental health risk assessment was performed following the US EPA framework, considering ingestion and dermal contact exposure pathways. Household risk perception and vulnerability were evaluated using the Household Water Insecurity Experiences (HWISE) questionnaire. The results showed that levels of Mn, NO3-, and total coliforms exceeded WHO guideline values at multiple sites, with the highest levels observed downstream, indicating cumulative urban influences on groundwater quality. In contrast, Fe and Zn concentrations remained low and within acceptable limits across all sites. Comparative analysis revealed that well water contained significantly higher levels of Mn, NO3-, and total coliforms than piped water, but not levels of Fe and Zn. Although contaminant concentrations were generally lower in piped water, ingestion remained the dominant pathway of potential health risk concern. While households demonstrated high awareness of water-related risks, preventive capacity differed between well-water and piped-water users. These findings underscore the need for integrated interventions combining risk communication, improved water quality monitoring, and expanded access to safe water in urban watershed settings.

在包括印度尼西亚在内的许多发展中国家，获得管道供水基础设施的机会有限，使得饮用水质量成为一个重要的公共卫生问题。在大雅加达人口稠密的城市地区，Ciliwung流域内的家庭继续严重依赖地下水，而地下水容易受到化学和微生物污染。本研究全面评估了饮用水质量，进行了筛查级环境健康风险评估，并评估了Ciliwung流域的家庭意识和预防能力。从流域上游、中游和下游4个地点采集水样，分析化学参数（Mn、NO3-、Fe和Zn）和微生物指标（总大肠菌群）。根据美国环保署的框架，考虑到摄入和皮肤接触暴露途径，进行了筛查水平的环境健康风险评估。使用家庭水不安全体验（HWISE）问卷对家庭风险感知和脆弱性进行评估。结果显示，多个站点的Mn、NO3-和总大肠菌群水平超过世卫组织指导值，其中下游地区的水平最高，表明城市对地下水质量的累积影响。相比之下，所有地点的铁和锌浓度仍然很低，在可接受的范围内。对比分析表明，井水的Mn、NO3-和总大肠菌群含量显著高于自来水，但铁和锌含量不显著高于自来水。虽然管道水中的污染物浓度普遍较低，但摄入仍然是潜在健康风险关注的主要途径。虽然家庭表现出对水相关风险的高度认识，但井水用户和管道水用户的预防能力不同。这些研究结果强调，需要采取综合干预措施，将风险沟通、改善水质监测和扩大城市流域安全用水的获取结合起来。

{"title":"Drinking water quality, environmental health risk assessment, and household perceptions of preventive capacity in the Ciliwung Watershed, Indonesia","authors":"Fitri Kurniasari , Bambang Wispriyono , Sifa Fauzia , Ghina Labibah , Alfian Fauzi Firdaus , Masashi Kato","doi":"10.1016/j.envc.2026.101416","DOIUrl":"10.1016/j.envc.2026.101416","url":null,"abstract":"<div><div>Limited access to piped water infrastructure has made drinking water quality a critical public health concern in many developing countries, including Indonesia. In densely populated urban areas of Greater Jakarta, households within the Ciliwung Watershed continue to rely heavily on groundwater sources that are vulnerable to chemical and microbiological contamination. This study comprehensively assessed drinking water quality, performed a screening-level environmental health risk assessment, and evaluated household awareness and preventive capacity in the Ciliwung Watershed. Water samples were collected from four locations representing upstream, midstream, and downstream sections of the watershed and analyzed for chemical parameters (Mn, NO3-, Fe, and Zn) and microbiological indicators (total coliforms). A screening-level environmental health risk assessment was performed following the US EPA framework, considering ingestion and dermal contact exposure pathways. Household risk perception and vulnerability were evaluated using the Household Water Insecurity Experiences (HWISE) questionnaire. The results showed that levels of Mn, NO3-, and total coliforms exceeded WHO guideline values at multiple sites, with the highest levels observed downstream, indicating cumulative urban influences on groundwater quality. In contrast, Fe and Zn concentrations remained low and within acceptable limits across all sites. Comparative analysis revealed that well water contained significantly higher levels of Mn, NO3-, and total coliforms than piped water, but not levels of Fe and Zn. Although contaminant concentrations were generally lower in piped water, ingestion remained the dominant pathway of potential health risk concern. While households demonstrated high awareness of water-related risks, preventive capacity differed between well-water and piped-water users. These findings underscore the need for integrated interventions combining risk communication, improved water quality monitoring, and expanded access to safe water in urban watershed settings.</div></div>","PeriodicalId":34794,"journal":{"name":"Environmental Challenges","volume":"22 ","pages":"Article 101416"},"PeriodicalIF":0.0,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077921","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}

引用次数: 0

Mosquito larvicide and adulticide impacts on western honey bee larvae (Apis mellifera) reared in vitro 杀蚊幼剂和杀成虫剂对体外饲养的西方蜜蜂幼虫的影响

Q2 Environmental Science

Environmental Challenges

Pub Date : 2026-01-23 DOI: 10.1016/j.envc.2026.101413

Lena Barascou , James D. Ellis , Cameron J. Jack

Effective mosquito control is essential for human health in many areas globally. However, some mosquito adulticides and larvicides administered by pesticide applicators could have non-target impacts, including on western honey bees (Apis mellifera). By elucidating the potential acute effects of mosquito adulticides and larvicides on honey bees, mosquito control personnel can work to minimize non-target impacts of pesticide applications. In this study, we exposed honey bee larvae to one of four mosquito adulticide active ingredients (chlorpyrifos, naled, prallethrin, sumithrin), their commercial formulations (Mosquito Mist®, Dibrom®, Duet®), or one larvicide (Bacillus thuringiensis israelensis - Bti). Honey bee larvae reared in vitro were exposed to pesticides in their diet on day three after grafting (acute exposure), or from days two to five after grafting (chronic exposure). We measured daily mortality and used these data to calculate the lethal dose that killed 50% of the population (LD₅₀) and the no-observed-adverse-effect-dose (NOAED) for each compound. We used the toxicity data to calculate risk quotients (RQs) using BeeRex. The RQs for the active ingredients suggest that the compounds are unlikely to affect larval mortality at the residue concentrations detected in hive matrices. However, under our in vitro conditions, the formulated mosquito adulticides Mosquito Mist®, Dibrom®, and Duet® caused the highest toxicity of the tested formulations to immature honey bees after chronic exposure, whereas only Dibrom® impacted immature honey bees after acute exposure. Bti demonstrated a higher risk than the other formulations to honey bee larvae only following acute exposure. The resulting data can be used to improve risk assessments for mosquito control products.

在全球许多地区，有效控制蚊子对人类健康至关重要。然而，一些杀虫剂施药器使用的杀蚊剂和杀幼虫剂可能产生非目标影响，包括对西方蜜蜂（Apis mellifera）的影响。通过阐明杀蚊剂和杀幼虫剂对蜜蜂的潜在急性影响，灭蚊人员可以努力减少农药施用的非目标影响。在这项研究中，我们将蜜蜂幼虫暴露于四种灭蚊活性成分（毒死蜱、萘啶菊酯、氯丙菊酯、氰菊酯）中的一种、它们的商业配方（灭蚊雾®、迪溴姆®、双溴醚®）或一种灭蚊剂（苏云金芽孢杆菌以色列- Bti）中。体外培养的蜜蜂幼虫在嫁接后第3天（急性暴露）或嫁接后第2 - 5天（慢性暴露）暴露于饲料中的农药。我们测量了每日死亡率，并利用这些数据计算了每种化合物致50%人口死亡的致死剂量（LD50）和未观察到的不良反应剂量（NOAED）。我们使用BeeRex软件计算毒性数据的风险商（RQs）。活性成分的RQs表明，在蜂房基质中检测到的残留浓度下，这些化合物不太可能影响幼虫的死亡率。然而，在体外条件下，配制的灭蚊剂mosquito Mist®、Dibrom®和Duet®在慢性暴露后对未成熟蜜蜂的毒性最高，而只有Dibrom®在急性暴露后对未成熟蜜蜂有影响。Bti仅在急性暴露后才比其他配方对蜜蜂幼虫有更高的风险。所得数据可用于改进蚊虫控制产品的风险评估。

{"title":"Mosquito larvicide and adulticide impacts on western honey bee larvae (Apis mellifera) reared in vitro","authors":"Lena Barascou , James D. Ellis , Cameron J. Jack","doi":"10.1016/j.envc.2026.101413","DOIUrl":"10.1016/j.envc.2026.101413","url":null,"abstract":"<div><div>Effective mosquito control is essential for human health in many areas globally. However, some mosquito adulticides and larvicides administered by pesticide applicators could have non-target impacts, including on western honey bees (<em>Apis mellifera</em>). By elucidating the potential acute effects of mosquito adulticides and larvicides on honey bees, mosquito control personnel can work to minimize non-target impacts of pesticide applications. In this study, we exposed honey bee larvae to one of four mosquito adulticide active ingredients (chlorpyrifos, naled, prallethrin, sumithrin), their commercial formulations (Mosquito Mist®, Dibrom®, Duet®), or one larvicide (<em>Bacillus thuringiensis israelensis</em> - Bti). Honey bee larvae reared <em>in vitro</em> were exposed to pesticides in their diet on day three after grafting (acute exposure), or from days two to five after grafting (chronic exposure). We measured daily mortality and used these data to calculate the lethal dose that killed 50% of the population (LD<sub>50</sub>) and the no-observed-adverse-effect-dose (NOAED) for each compound. We used the toxicity data to calculate risk quotients (RQs) using BeeRex. The RQs for the active ingredients suggest that the compounds are unlikely to affect larval mortality at the residue concentrations detected in hive matrices. However, under our <em>in vitro</em> conditions, the formulated mosquito adulticides Mosquito Mist®, Dibrom®, and Duet® caused the highest toxicity of the tested formulations to immature honey bees after chronic exposure, whereas only Dibrom® impacted immature honey bees after acute exposure. Bti demonstrated a higher risk than the other formulations to honey bee larvae only following acute exposure. The resulting data can be used to improve risk assessments for mosquito control products.</div></div>","PeriodicalId":34794,"journal":{"name":"Environmental Challenges","volume":"22 ","pages":"Article 101413"},"PeriodicalIF":0.0,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146038090","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}

引用次数: 0

Climate action strategies for sustainable rainfed agricultural systems in Southern India: Economic and crop modeling insights 南印度可持续雨养农业系统的气候行动战略：经济和作物建模见解

Q2 Environmental Science

Environmental Challenges

Pub Date : 2026-01-20 DOI: 10.1016/j.envc.2026.101412

V.S. Manivasagam , P.R. Anuranj , S. Parvathy , Raida Rasheed , S. Adithya Krishna , P.R. Akhil , Gautham Prakash , Sudheesh Manalil , Tamilarasu Arivelarasan

Disrupted rainfall patterns and rising temperature anomalies pose significant threats to global food security, particularly by increasing the risk of crop failures and reducing agricultural productivity in rainfed systems. This study evaluates the future feasibility of practicing rainfed cropping in peninsular India by introducing a novel crop viability index, derived from the latest CMIP6 climate projections and the CROPWAT model. Based on this index, the regions are grouped into four distinct zones from safe to high-risk zone of rainfed cultivation. The study further examines the impact of seven field-scale climate adaptation strategies on sustaining crop cultivation in rainfed areas and assesses their economic viability for each zone. The study findings reveal that 44% of rainfed districts in peninsular India are projected to face drought risk in the near future. Furthermore, the study also demonstrates that a combination of early sowing, drought-tolerant crop varieties, and farm pond construction would be the most effective climate response strategy. The proposed assessment framework provides region specific recommendations and serves as a strategic roadmap for enhancing the sustainability and resilience of rainfed farming systems.

降雨模式中断和温度异常上升对全球粮食安全构成重大威胁，特别是增加了作物歉收的风险，降低了雨养系统的农业生产力。本研究通过引入一种新的作物活力指数来评估印度半岛实行雨养作物的未来可行性，该指数来源于最新的CMIP6气候预测和CROPWAT模型。在此基础上，从旱作安全区到旱作高风险区，将这些地区划分为4个不同的区域。该研究进一步考察了7种大田尺度的气候适应策略对雨养地区维持作物种植的影响，并评估了它们在每个地区的经济可行性。研究结果显示，在不久的将来，印度半岛44%的雨养地区预计将面临干旱风险。此外，研究还表明，早期播种、耐旱作物品种和农场池塘建设相结合将是最有效的气候应对策略。拟议的评估框架提供了区域具体建议，并作为加强雨养农业系统可持续性和复原力的战略路线图。

{"title":"Climate action strategies for sustainable rainfed agricultural systems in Southern India: Economic and crop modeling insights","authors":"V.S. Manivasagam , P.R. Anuranj , S. Parvathy , Raida Rasheed , S. Adithya Krishna , P.R. Akhil , Gautham Prakash , Sudheesh Manalil , Tamilarasu Arivelarasan","doi":"10.1016/j.envc.2026.101412","DOIUrl":"10.1016/j.envc.2026.101412","url":null,"abstract":"<div><div>Disrupted rainfall patterns and rising temperature anomalies pose significant threats to global food security, particularly by increasing the risk of crop failures and reducing agricultural productivity in rainfed systems. This study evaluates the future feasibility of practicing rainfed cropping in peninsular India by introducing a novel crop viability index, derived from the latest CMIP6 climate projections and the CROPWAT model. Based on this index, the regions are grouped into four distinct zones from safe to high-risk zone of rainfed cultivation. The study further examines the impact of seven field-scale climate adaptation strategies on sustaining crop cultivation in rainfed areas and assesses their economic viability for each zone. The study findings reveal that 44% of rainfed districts in peninsular India are projected to face drought risk in the near future. Furthermore, the study also demonstrates that a combination of early sowing, drought-tolerant crop varieties, and farm pond construction would be the most effective climate response strategy. The proposed assessment framework provides region specific recommendations and serves as a strategic roadmap for enhancing the sustainability and resilience of rainfed farming systems.</div></div>","PeriodicalId":34794,"journal":{"name":"Environmental Challenges","volume":"22 ","pages":"Article 101412"},"PeriodicalIF":0.0,"publicationDate":"2026-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146038089","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}

引用次数: 0

Achieving zero hunger: A global policy lens on food security drivers and income group disparities 实现零饥饿：粮食安全驱动因素和收入群体差距的全球政策视角

Q2 Environmental Science

Environmental Challenges

Pub Date : 2026-01-19 DOI: 10.1016/j.envc.2026.101409

Nirmani Pulle , Prasad Sampath , Sarah Perera , Dinuli Wijayaweera , Ruwan Jayathilaka

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.

尽管许多国家尝试解决现有的需求，但仍难以满足其日常饮食需求。因此，本研究基于森的权利理论，对城市化、可再生能源、温室气体排放、人口增长、人均国内生产总值和农业用地对粮食生产的影响进行了综合分析，从而为解决长期存在的粮食不安全问题提供见解，为实现可持续发展目标提供支持。该研究采用了一个逐步排序的Probit模型，对146个国家进行了1993年至2023年的调查。它进一步将粮食生产指数分为三类粮食安全：低、中等和高，从而能够讨论一个国家多年来落入上述粮食安全类别之一的可能性。城市化、农业用地和用于表示收入群体的虚拟变量已被确定与粮食生产指数有显著和有利的关系。相反，温室气体排放和可再生能源变量对粮食生产指数有显著的反向影响。这对现有文献做出了独特的贡献，特别是通过比较多年来不同粮食安全类别、国家及其特定收入水平的赔率。这项研究使决策者能够对每个案例获得全面的历史视角。这项研究进一步促进了可持续发展目标，突出了这些目标受到负面影响的领域。此外，该研究还讨论了优化投资分配、农业研发、农业技术、气候适应型农业和可持续城市化规划等极端案例的解决方案。

{"title":"Achieving zero hunger: A global policy lens on food security drivers and income group disparities","authors":"Nirmani Pulle , Prasad Sampath , Sarah Perera , Dinuli Wijayaweera , 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":"2026-01-19","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}

引用次数: 0

Toward integrated coastal special economic zones: A review of agro-marine industry, renewable energy, and circular economy synergies 迈向一体化沿海经济特区：农海产业、可再生能源与循环经济协同效应研究综述

Q2 Environmental Science

Environmental Challenges

Pub Date : 2026-01-19 DOI: 10.1016/j.envc.2026.101410

Erkata Yandri , Ambo Tuwo , Winarni Dien Monoarfa

Coastal Special Economic Zones (CSEZs) are increasingly promoted as engines of blue growth and coastal development, yet their implementation often remains fragmented across agro-marine production systems, energy provision, and resource management strategies. While existing studies have examined agro-marine industries, renewable energy deployment, and circular economy practices in coastal contexts, an integrated synthesis explicitly framed within CSEZs remains limited. This review addresses this gap by synthesizing peer-reviewed literature on agro-marine–oriented CSEZs to identify key patterns, challenges, and opportunities for integrated coastal development. Using a structured narrative review approach, 218 peer-reviewed articles were screened and analyzed through an inductive thematic synthesis. The literature was organized into four thematic domains: CSEZs, agro-marine industry development, coastal renewable energy utilization, and coastal circular economy strategies. Across these domains, the review synthesizes points of agreement, differences, emerging themes, and critical research gaps. The findings indicate that integrated CSEZ designs, embedding agro-marine value chains, renewable energy enablement, and circular economy principles within coherent governance and spatial planning frameworks, can enhance climate resilience, reduce environmental pressures, and support inclusive coastal livelihoods. This review presents a structured integrative framework that clarifies how agro-marine production systems, renewable energy enablement, and circular economic strategies interact within CSEZs, providing a conceptual foundation to inform future empirical research, comparative assessment, and policy design in emerging coastal economies.

沿海经济特区（CSEZs）作为蓝色增长和沿海发展的引擎日益得到推广，但其实施往往在农业-海洋生产系统、能源供应和资源管理战略方面仍然支离破碎。虽然现有的研究已经考察了沿海地区的农业海洋产业、可再生能源部署和循环经济实践，但在经济特区内明确构建的综合综合仍然有限。本文通过综合以农业海洋为导向的经济特区的同行评议文献，确定沿海综合发展的主要模式、挑战和机遇，解决了这一差距。采用结构化的叙事评论方法，218篇同行评议文章通过归纳主题综合进行筛选和分析。文献分为四个主题领域：经济特区、农水产业发展、沿海可再生能源利用和沿海循环经济战略。在这些领域中，综述综合了共识、分歧、新兴主题和关键研究差距。研究结果表明，综合经济特区设计，将农海价值链、可再生能源支持和循环经济原则纳入连贯的治理和空间规划框架，可以增强气候适应能力，减少环境压力，并支持包容性沿海生计。本综述提出了一个结构化的综合框架，阐明了农业-海洋生产系统、可再生能源支持和循环经济战略如何在经济特区内相互作用，为新兴沿海经济体未来的实证研究、比较评估和政策设计提供了概念基础。

{"title":"Toward integrated coastal special economic zones: A review of agro-marine industry, renewable energy, and circular economy synergies","authors":"Erkata Yandri , Ambo Tuwo , Winarni Dien Monoarfa","doi":"10.1016/j.envc.2026.101410","DOIUrl":"10.1016/j.envc.2026.101410","url":null,"abstract":"<div><div>Coastal Special Economic Zones (CSEZs) are increasingly promoted as engines of blue growth and coastal development, yet their implementation often remains fragmented across agro-marine production systems, energy provision, and resource management strategies. While existing studies have examined agro-marine industries, renewable energy deployment, and circular economy practices in coastal contexts, an integrated synthesis explicitly framed within CSEZs remains limited. This review addresses this gap by synthesizing peer-reviewed literature on agro-marine–oriented CSEZs to identify key patterns, challenges, and opportunities for integrated coastal development. Using a structured narrative review approach, 218 peer-reviewed articles were screened and analyzed through an inductive thematic synthesis. The literature was organized into four thematic domains: CSEZs, agro-marine industry development, coastal renewable energy utilization, and coastal circular economy strategies. Across these domains, the review synthesizes points of agreement, differences, emerging themes, and critical research gaps. The findings indicate that integrated CSEZ designs, embedding agro-marine value chains, renewable energy enablement, and circular economy principles within coherent governance and spatial planning frameworks, can enhance climate resilience, reduce environmental pressures, and support inclusive coastal livelihoods. This review presents a structured integrative framework that clarifies how agro-marine production systems, renewable energy enablement, and circular economic strategies interact within CSEZs, providing a conceptual foundation to inform future empirical research, comparative assessment, and policy design in emerging coastal economies.</div></div>","PeriodicalId":34794,"journal":{"name":"Environmental Challenges","volume":"22 ","pages":"Article 101410"},"PeriodicalIF":0.0,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146038091","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}

引用次数: 0

Improving the transferability of SAR-derived vegetation indices for crop monitoring 提高sar衍生植被指数在作物监测中的可转移性

Q2 Environmental Science

Environmental Challenges

Pub Date : 2026-01-19 DOI: 10.1016/j.envc.2026.101411

Henry Poku Osei, Anita Simic Milas, Mir Md Tasnim Alam

Optical vegetation indices (VIs) are widely used for crop monitoring, yet their operational value is often limited by cloud contamination and data gaps. Synthetic aperture radar (SAR) provides cloud-independent observations and is sensitive to crop structure, offering a pathway to estimate VIs when optical imagery is unavailable. A key challenge, however, is the transferability of SAR-based VI models across regions and seasons due to environmental and climatic differences. Here, we evaluated whether incorporating time-related proxies of crop growth such as accumulated growing degree days (AGDD) and days after planting (DAP), together with environmental variables can improve the transferability of SAR-estimated VIs across major U.S. corn and soybean production regions. Using dense Sentinel-1 SAR with Harmonized Landsat–Sentinel (HLS) reference data, we trained LightGBM regression models under multiple predictor configurations. Across climate zones, adding time-related features consistently improved generalization relative to SAR-only baselines, with DAP providing the most robust performance. For NDVI, the DAP-based model achieved MAE values ranging from 0.083 to 0.115 and R² scores between 0.422 and 0.781. For EVI, the model achieved MAE values ranging from 0.081 to 0.111 and R² scores between 0.388 and 0.721. Performance peaked in humid continental zones (Dfa/Dfb) but declined in semi-arid (BSk) and subtropical zones (Cfa), where unaccounted moisture and biotic stressors limited spatial transferability. This study offers insights into developing a scalable framework that ensures high-frequency crop monitoring across diverse geographies.

光学植被指数（VIs）广泛用于作物监测，但其操作价值往往受到云污染和数据空白的限制。合成孔径雷达（SAR）提供与云无关的观测，对作物结构敏感，在没有光学图像时提供了估计VIs的途径。然而，一个关键的挑战是，由于环境和气候的差异，基于sar的VI模型在不同地区和季节的可转移性。在这里，我们评估了将作物生长的时间相关指标（如累积生长度日数（AGDD）和种植后日数（DAP））与环境变量结合是否可以改善sar估计的VIs在美国主要玉米和大豆产区的可转移性。利用具有协调Landsat-Sentinel （HLS）参考数据的高密度Sentinel-1 SAR，我们在多种预测器配置下训练了LightGBM回归模型。在各个气候带中，与仅使用sar的基线相比，添加与时间相关的特征持续提高了泛化效果，其中DAP提供了最稳健的性能。对于NDVI，基于dap的模型的MAE值在0.083 ~ 0.115之间，R²得分在0.422 ~ 0.781之间。对于EVI，模型的MAE值在0.081 ~ 0.111之间，R²得分在0.388 ~ 0.721之间。在湿润大陆区（Dfa/Dfb）表现最高，但在半干旱区（BSk）和亚热带区（Cfa）表现下降，其中未解释的水分和生物压力因素限制了空间可转移性。这项研究为开发一个可扩展的框架提供了见解，该框架可确保在不同地区对作物进行高频监测。

{"title":"Improving the transferability of SAR-derived vegetation indices for crop monitoring","authors":"Henry Poku Osei, Anita Simic Milas, Mir Md Tasnim Alam","doi":"10.1016/j.envc.2026.101411","DOIUrl":"10.1016/j.envc.2026.101411","url":null,"abstract":"<div><div>Optical vegetation indices (VIs) are widely used for crop monitoring, yet their operational value is often limited by cloud contamination and data gaps. Synthetic aperture radar (SAR) provides cloud-independent observations and is sensitive to crop structure, offering a pathway to estimate VIs when optical imagery is unavailable. A key challenge, however, is the transferability of SAR-based VI models across regions and seasons due to environmental and climatic differences. Here, we evaluated whether incorporating time-related proxies of crop growth such as accumulated growing degree days (AGDD) and days after planting (DAP), together with environmental variables can improve the transferability of SAR-estimated VIs across major U.S. corn and soybean production regions. Using dense Sentinel-1 SAR with Harmonized Landsat–Sentinel (HLS) reference data, we trained LightGBM regression models under multiple predictor configurations. Across climate zones, adding time-related features consistently improved generalization relative to SAR-only baselines, with DAP providing the most robust performance. For NDVI, the DAP-based model achieved MAE values ranging from 0.083 to 0.115 and R² scores between 0.422 and 0.781. For EVI, the model achieved MAE values ranging from 0.081 to 0.111 and R² scores between 0.388 and 0.721. Performance peaked in humid continental zones (Dfa/Dfb) but declined in semi-arid (BSk) and subtropical zones (Cfa), where unaccounted moisture and biotic stressors limited spatial transferability. This study offers insights into developing a scalable framework that ensures high-frequency crop monitoring across diverse geographies.</div></div>","PeriodicalId":34794,"journal":{"name":"Environmental Challenges","volume":"22 ","pages":"Article 101411"},"PeriodicalIF":0.0,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146038086","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}

引用次数: 0

Advancing irrigated area mapping using machine learning and deep learning approaches: The case of Awash Valley, Ethiopia 利用机器学习和深度学习方法推进灌溉区测绘：以埃塞俄比亚阿瓦什谷为例

Q2 Environmental Science

Environmental Challenges

Pub Date : 2026-01-14 DOI: 10.1016/j.envc.2026.101408

Berhan Gessesse , Gebeyehu Abebe , Gezahagn Woldu , Zerihun Chere

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.

为了加强国家粮食安全抵御能力，需要获得埃塞俄比亚干旱低地灌溉农田的准确和及时数据。然而，传统的测绘方法仍然不能提供关于灌溉农业实践的准确信息。本研究通过使用先进的机器学习（如SVM， RF）和最先进的深度学习（ResUNet）评估多源地球观测（EO）数据来解决这些差距。利用Sentinel-2 Level 2（S2A）遥感影像，设计了3种分类场景：1)6个光谱波段；ii)光谱带加3个植被指数，包括增强植被指数（EVI）、归一化植被指数（NDVI）和陆地地表水指数（LSWI）；iii)包含光谱纹理度量（如方差、对比度和不相似性）的扩展特征集。这些模型为量化阿瓦什流域的灌溉区提供了一个强有力的框架，克服了传统数据的限制。使用地面参考数据严格验证了模型输出。本研究评估了ResUNet深度学习架构在埃塞俄比亚异质阿瓦什盆地景观精确灌溉和土地利用测绘方面的变革潜力。通过整合多光谱波段、植被指数和光谱特征，ResUNet的总体精度为84.13%，Kappa为0.83，显著优于SVM（67.54%）和Random Forest（82.33%）。该模型的残差学习框架被证明对于捕获半干旱区复杂的空间光谱层次至关重要，在灌溉区检测中达到了0.89的峰值f1分。除了技术性能之外，这种自动化方法还提供了必要的监测能力，以支持水资源管理、干旱预警系统和小农的粮食安全评估。

{"title":"Advancing irrigated area mapping using machine learning and deep learning approaches: The case of Awash Valley, Ethiopia","authors":"Berhan Gessesse , Gebeyehu Abebe , Gezahagn Woldu , 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":"2026-01-14","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}

引用次数: 0