Yating Ru , Elizabeth Tennant , David S. Matteson , Christopher B. Barrett
{"title":"Spatial heterogeneity in machine learning-based poverty mapping: Where do models underperform?","authors":"Yating Ru , Elizabeth Tennant , David S. Matteson , Christopher B. Barrett","doi":"10.1016/j.geosus.2026.100413","DOIUrl":"10.1016/j.geosus.2026.100413","url":null,"abstract":"<div><div>Accurately locating poor populations is increasingly urgent as global poverty reduction has stalled under the combined pressures of conflicts, climate shocks, rising food prices, pandemics, and growing inequality. Recent studies harnessing geospatial big data and machine learning (ML) have significantly advanced poverty mapping, enabling granular and timely welfare estimates in traditionally data-scarce regions. While much of the existing research has focused on overall out-of-sample predictive performance, there is a lack of understanding regarding where such models underperform and whether key spatial relationships might vary across places. This study investigates spatial heterogeneity in ML-based poverty mapping in East Africa, testing whether spatial regression and ML techniques produce more unbiased predictions. We find that extrapolation into unsurveyed areas suffers from biases that spatial methods do not resolve; welfare is overestimated in impoverished regions, rural areas, and single sector-focused economies, whereas it tends to be underestimated in wealthier, urbanized, and diversified economies. Even as spatial models improve overall predictive accuracy, enhancements in traditionally underperforming areas remain marginal. This underscores the need for more representative training datasets and better remotely sensed proxies, especially for poor and rural regions, in future research related to ML-based poverty mapping. For development agencies, the findings caution against treating ML-based outputs as neutral or universally reliable, highlighting instead the need to pair technical advances with investments in inclusive data collection, integration of spatial theory, and institutional strategies that address structural data inequalities.</div></div>","PeriodicalId":52374,"journal":{"name":"Geography and Sustainability","volume":"7 2","pages":"Article 100413"},"PeriodicalIF":8.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146081930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Paulo Pereira , Miguel Inacio , Damia Barcelo , Wenwu Zhao
{"title":"Reply to Bullock et al. (2026) on ecosystem service models are indeed being validated","authors":"Paulo Pereira , Miguel Inacio , Damia Barcelo , Wenwu Zhao","doi":"10.1016/j.geosus.2026.100462","DOIUrl":"10.1016/j.geosus.2026.100462","url":null,"abstract":"","PeriodicalId":52374,"journal":{"name":"Geography and Sustainability","volume":"7 2","pages":"Article 100462"},"PeriodicalIF":8.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147656772","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mengzhu Liu , Yilin Shen , Ying Guo , Lili Yu , Yongqing Qi , Bojie Fu , Yanjun Shen
{"title":"Hidden costs of a thriving Yellow River: Severe groundwater depletion","authors":"Mengzhu Liu , Yilin Shen , Ying Guo , Lili Yu , Yongqing Qi , Bojie Fu , Yanjun Shen","doi":"10.1016/j.geosus.2026.100407","DOIUrl":"10.1016/j.geosus.2026.100407","url":null,"abstract":"<div><div>Groundwater storage (GWS) is essential for supporting agricultural irrigation and revegetation in the water-scarce Yellow River Basin (YRB). Early studies have mainly focused on the impacts of revegetation on GWS, and rarely consider the influences of agricultural irrigation and other human activities, rendering the driving mechanisms of GWS unclear. Here we used NASA’s Gravity Recovery and Climate Experiment (GRACE) satellite data, the PCR-GLOBWB2 hydrologic model, and an Long Short-Term Memory (LSTM) machine learning approach to reveal changes, driving mechanisms, and future trends in GWS in the YRB. Results show that GWS in the YRB decreased by ∼101 Gt in 2003−2020, roughly 24 times the Yellow River’s flow into the sea in 2000. Notably, GWS depletion (−7.7 mm/yr) dominates the observed terrestrial water storage (TWS) losses (−6.0 mm/yr) and accounts for >100% of the net TWS decline. Storage losses are largely explained by increases in evapotranspiration (+6.0 mm/yr) driven by revegetation and agricultural irrigation. This is evident in higher evapotranspiration rates (+3 mm/yr) observed in heavily revegetated areas, with irrigation showing an estimated contribution of −6.6 mm/yr on GWS by the PCR-GLOBWB2 model. GWS losses are projected to persist until 2060 by the LSTM model, with a total storage loss of ∼237 Gt. With GWS declining and natural recharge growth lagging behind the rise in groundwater demand, the YRB confronts a future of groundwater deficits. The study suggests that although groundwater extraction for agricultural and ecological benefits might appear helpful to the region in the short term, this trajectory is physically unsustainable and detrimental to the water-scarce Yellow River.</div></div>","PeriodicalId":52374,"journal":{"name":"Geography and Sustainability","volume":"7 2","pages":"Article 100407"},"PeriodicalIF":8.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146057593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tongning Li , Guoen Wei , Minghui Xu , Daozheng Li , Weifeng Deng , Yaobin Liu , Bao-Jie He
{"title":"Spatio-temporal responses of ecological resilience to urbanization in five Great Lakes Regions (GLRs) in China and implications for building resilient GLRs","authors":"Tongning Li , Guoen Wei , Minghui Xu , Daozheng Li , Weifeng Deng , Yaobin Liu , Bao-Jie He","doi":"10.1016/j.geosus.2025.100395","DOIUrl":"10.1016/j.geosus.2025.100395","url":null,"abstract":"<div><div>Great Lakes Regions (GLRs) in China often confront landscape fragmentation, wetland degradation, and ecological resilience (ER) losses owing to extensive and intensive urbanization. In GLRs, however, the ER responses to urbanization remain unclear. This study explored the spatiotemporal evolution of ER and urbanization in five GLRs in China to analyze the ER dynamic patterns along center−lakeside−periphery gradient. The Spatial Durbin Model (SDM) and Panel Threshold Model (PTM) were combined to reveal the spillover and threshold effects of urbanization in five GLRs. The results indicate that the ER in five GLRs declined with a rate of 21 % from 2000 to 2020. There was a clear “center-periphery” contraction trend with low ER areas primarily spreading to human activity-concentrated regions such as lakesides, riversides, and road networks. Driven by economic and land urbanization, the average urbanization level increased from 0.06 to 0.13, where lakesides, riversides, and road networks were key areas undergoing expansion. The urbanization showed a noticeable negative spatial spillover effect on ER. Away from central lakes, the negative impacts on ER exhibited a two-phase decrease with the threshold of 81 km. This study contributes to the understanding of human-environment interactions by examining the ecological resilience response process of GLRs under the impact of urbanization. Based on a multidimensional “center−lakeside−periphery” analytical model, this study provides a strategic framework for ecological construction in GLRs in China, promoting sustainable development and adaptive capacity in vulnerable areas.</div></div>","PeriodicalId":52374,"journal":{"name":"Geography and Sustainability","volume":"7 1","pages":"Article 100395"},"PeriodicalIF":8.0,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146038293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Daoming Ma , Yang Yu , Ming Gong , Zhiqiang Zhang , Steven A Kannenberg
{"title":"Recent widespread forest expansion and densification in Southwest China","authors":"Daoming Ma , Yang Yu , Ming Gong , Zhiqiang Zhang , Steven A Kannenberg","doi":"10.1016/j.geosus.2025.100404","DOIUrl":"10.1016/j.geosus.2025.100404","url":null,"abstract":"<div><div>Large-scale afforestation and forest conservation policies have been widely implemented in Southwest China over past decades. These efforts have significantly protected the remaining long-established forests in the region and greatly expanded forested areas. Utilizing nearly 30 years of satellite time-series data, we reveal that the region’s enhanced carbon sequestration (3 × 10<sup>12</sup> g·C annually) is primarily driven by crucial changes in forest structure and age, occurring alongside a nearly 120 % increase in forested land area. We observe that dense forests maintain a rapid growth rate of approximately 2.5 % annually for carbon sequestration in the initial years after establishment. However, this growth rate decelerates with increasing apparent forest age. Meanwhile, the densification (modeled as an increasing forest probability) rate of forests reaches its peak growth during the 10–20 year period, sustaining a high annual growth rate of about 1.8 %. We also find that improvements in forest structure, particularly the increasing of forest canopy density and apparent forest age coupled with a notable reduction in forest fragmentation, are also the main driving factors for the enhanced carbon sequestration capacity. Based on these findings, we conclude that forest restoration policies in Southwest China have been successful not only in facilitating large-scale forest growth in Southwest China but, more critically, in promoting the structural maturation (e.g., densification and reduced fragmentation) that is essential for enhancing the region’s carbon sink capacity and its resilience.</div></div>","PeriodicalId":52374,"journal":{"name":"Geography and Sustainability","volume":"7 1","pages":"Article 100404"},"PeriodicalIF":8.0,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146038290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hao Wu , Ping Zhang , Jun Chen , Songnian Li , Jing Li , Shu Peng , Dongyang Hou , Jun Zhang , Hao Chen
{"title":"A data- and expert-driven framework for establishing land cover–related essential variables for SDG monitoring and assessment","authors":"Hao Wu , Ping Zhang , Jun Chen , Songnian Li , Jing Li , Shu Peng , Dongyang Hou , Jun Zhang , Hao Chen","doi":"10.1016/j.geosus.2025.100397","DOIUrl":"10.1016/j.geosus.2025.100397","url":null,"abstract":"<div><div>Sustained and spatially explicit monitoring of the United Nations 2030 Agenda for Sustainable Development is critical for effectively tracking progress toward the global Sustainable Development Goals (SDGs). Although land cover information has long been recognized as an essential component for monitoring SDGs, a standardized scientific framework for identifying and prioritizing land cover related essential variables does not exist. Therefore, we propose a novel expert- and data-driven framework for identifying, refining, and selecting a priority list of Essential Land cover-related Variables for SDGs (ELcV4SDGs). This framework integrates methods including expert knowledge-based analysis, clustering of variables with similar attributes, and quantified index calculation to establish the priority list. Applying the framework to 15 specific SDG indicators, we found that the ELcV4SDGs priority list comprises three main categories, type and structure, pattern and intensity, and process and evolution of land cover, which are further divided into 19 subcategories and ultimately encompass 50 general variables. The ELcV4SDGs will support detailed spatial monitoring and enhance their scientific applications for SDG monitoring and assessment, thereby guiding future SDG priority actions and informing decision-making to advance the 2030 SDGs agenda at local, national, and global levels.</div></div>","PeriodicalId":52374,"journal":{"name":"Geography and Sustainability","volume":"7 1","pages":"Article 100397"},"PeriodicalIF":8.0,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145941338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jinran Wu , Xin Tian , You-Gan Wang , Tong Li , Qingyang Liu , Yayong Li , Lizhen Cui , Zhuangcai Tian , Jing Xu , Xianzhou Lyu , Yuming Mo
{"title":"AI ethics in geoscience: Toward trustworthy and responsible innovation","authors":"Jinran Wu , Xin Tian , You-Gan Wang , Tong Li , Qingyang Liu , Yayong Li , Lizhen Cui , Zhuangcai Tian , Jing Xu , Xianzhou Lyu , Yuming Mo","doi":"10.1016/j.geosus.2026.100414","DOIUrl":"10.1016/j.geosus.2026.100414","url":null,"abstract":"","PeriodicalId":52374,"journal":{"name":"Geography and Sustainability","volume":"7 1","pages":"Article 100414"},"PeriodicalIF":8.0,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146188771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zihan Xu , Tianyi Wu , Tao Hu , Yanxu Liu , Jian Peng
{"title":"International food trade increased the food security gap between high and low economic development groups","authors":"Zihan Xu , Tianyi Wu , Tao Hu , Yanxu Liu , Jian Peng","doi":"10.1016/j.geosus.2025.100402","DOIUrl":"10.1016/j.geosus.2025.100402","url":null,"abstract":"<div><div>International trade serves as a crucial pathway for enhancing global food security and equality amid severe food crises worldwide. Under globalization, economic development has profoundly influenced food trade, while disparities in food purchasing power among different economic development groups have led to uneven food security outcomes. However, the varying contributions of international trade to food security across these groups remain to be quantitatively elucidated. This study categorized countries into four economic development groups—high, high-medium, medium-low, and low—and examined changes in their food security scores from 2010 to 2019. The cross-group contributions of international trade to food security across these groups were compared. The results revealed that the food security score of the high economic development group was 9.22 times higher than that of the low economic development group. From 2010 to 2019, the high economic development group exhibited a significant upward trend in food security scores, whereas the low economic development group showed a significant decline. Moreover, international trade contributed significantly to both cross-group and within-group food security in the high economic development group, while its contribution to the low economic development group remained negligible. These findings demonstrated that international trade has further widened the food security gap between the high and low economic development groups, and its limited contribution to the low economic development group has failed to reverse the declining trend in their food security scores. This study quantified the divergent impacts of international trade on food security across economic development groups, providing valuable insights for optimizing global food trade policies—particularly in addressing the food security challenges faced by low econominc development group.</div></div>","PeriodicalId":52374,"journal":{"name":"Geography and Sustainability","volume":"7 1","pages":"Article 100402"},"PeriodicalIF":8.0,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145980677","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yiliang Li , Kaixuan Yao , Qingxiang Meng , Yujie Wang , Rui Xiao , Yuhang Liu , Sensen Wu , Yansheng Li
{"title":"Dynamic patterns and driving factors of productive cropland in Ukraine before and after Russia-Ukraine conflict","authors":"Yiliang Li , Kaixuan Yao , Qingxiang Meng , Yujie Wang , Rui Xiao , Yuhang Liu , Sensen Wu , Yansheng Li","doi":"10.1016/j.geosus.2025.100401","DOIUrl":"10.1016/j.geosus.2025.100401","url":null,"abstract":"<div><div>Ukraine, as one of the world’s largest agricultural producers and exporters, plays a critical role in global food security. It is essential to understand the spatiotemporal dynamics and drivers of productive cropland in Ukraine, particularly in the context of the 2022 Russia-Ukraine conflict. We provide the first comprehensive assessment of both conflict- and non-conflict-related factors that influenced the distribution and productivity of Ukraine’s cropland from 2013 to 2023. In addition, we propose a novel method using machine learning models to isolate the impact of conflict on cropland. Our findings reveal that, prior to the conflict, the spatial pattern of Ukraine’s mean cultivation rate was primarily shaped by natural factors—such as climate, soil properties, and elevation—whereas socio-economic factors (e.g., GDP and population size) exerted a weaker influence. Interannual dynamics in productive cropland area were largely driven by climate variability. The onset of conflict in 2022 dramatically altered this landscape, with nearly half of the cropland grid cells experiencing a conflict-induced reduction. Notably, almost half of the interannual reduction in productive cropland in 2022 was attributed to climate change. Remarkably, in 2023, the return of displaced populations and favorable climatic conditions in many oblasts contributed to a positive trend in cropland reclamation. Despite this, the total area of productive cropland in 2023 remained below expected levels, due to ongoing conflict and localized droughts. Finally, we highlight the urgent need to adopt a two-pronged approach that addresses both the immediate impacts of conflict and the ongoing threats posed by climate change to ensure the resilience and sustainability of agricultural systems in post-conflict areas.</div></div>","PeriodicalId":52374,"journal":{"name":"Geography and Sustainability","volume":"7 1","pages":"Article 100401"},"PeriodicalIF":8.0,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145980678","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zonghan Ma , Bingfang Wu , Nana Yan , Weiwei Zhu , Mengxiao Li , Hongwei Zeng , Yixuan Wang , Peilin Song , Qiquan Yang , Qingcheng Pan
{"title":"A basin-scale water budget calibration method for sustainable water management: A case study in the Loess Plateau, China","authors":"Zonghan Ma , Bingfang Wu , Nana Yan , Weiwei Zhu , Mengxiao Li , Hongwei Zeng , Yixuan Wang , Peilin Song , Qiquan Yang , Qingcheng Pan","doi":"10.1016/j.geosus.2025.100400","DOIUrl":"10.1016/j.geosus.2025.100400","url":null,"abstract":"<div><div>Accurate water budget closure is critical for sustainable water resource management facing increased pressures from climate change and human activities. Although error reduction methods for individual water balance components have advanced, persistent biases remain due to the independent development of datasets, impacting basin scale water budget balance. In this research, we analyzed the mathematical origin of the bias between water budget components and developed a new basin-scale water balance calibration method that redistributes errors across components while enforcing water balance constraints. Validation confirms systematic improvements, with reduced RMSE (Precipitation: -2.29 mm/month; ET: -1.34 mm/month) and increased <em>R</em>² against in situ observations. Applied to the Jinghe River Basin (2000−2019), the calibrated data reveal declining precipitation (-1.70 mm/year) and evapotranspiration (-1.84 mm/year) alongside slightly increasing runoff (0.20 mm/year in basin depth), signaling a drying trend. Land cover changes—marked by cropland loss (-3,497 km²) and forest (+720 km²) and grassland (+2,776 km²) expansion—reflect improved water consumption requirements by ecosystem, raising concerns for water retention and ecosystem stability. The method is particularly effective for ungauged basins with sparse ground data and underscores the need for integrated land-water management to enhance long-term resilience.</div></div>","PeriodicalId":52374,"journal":{"name":"Geography and Sustainability","volume":"7 1","pages":"Article 100400"},"PeriodicalIF":8.0,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145980679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}