Multi-objective ecological restoration priority in China: Cost-benefit optimization in different ecological performance regimes based on planetary boundaries

Journal of Environmental Management, Journal Year: 2024, Volume and Issue: 356, P. 120701 - 120701

Published: March 26, 2024

Language: Английский

---

Enhancing wildfire mapping accuracy using mono-temporal Sentinel-2 data: A novel approach through qualitative and quantitative feature selection with explainable AI

Ecological Informatics, Journal Year: 2024, Volume and Issue: 81, P. 102601 - 102601

Published: April 16, 2024

Accurate wildfire severity mapping (WSM) is crucial in environmental damage assessment and recovery strategies. Machine learning (ML) remote sensing technologies are extensively integrated employed as powerful tools for WSM. However, the intricate nature of ML algorithms often leads to 'black box' systems, obscuring decision-making process significantly limiting stakeholders' ability comprehend basis predictions. This opacity hinders efforts enhance performance risks exacerbating overfitting. present study proposes an innovative WSM approach that incorporates qualitative quantitative feature selection techniques within Explainable AI (XAI) framework. The methodology aims precision provide insights into factors contributing model decisions, thereby increasing interpretability predictions streamlining models improve performance. To achieve this objective, we SHapley Additive exPlanations (SHAP)-Forward Stepwise Selection (FSS) method demonstrate its efficacy elucidating impacts predictors on algorithm performance, accuracy, designed Utilizing post-fire imagery from Sentinel-2 (S2), analyzed ten bands generate 225 unique spectral indices utilizing five different calculations: normalized, algebraic sum, difference, ratio, product forms. Combined with original S2 bands, resulted 235 potential classifications. A random forest was subsequently developed using these optimized through extensive hyperparameter tuning, achieving overall accuracy (OA) 0.917 a Kappa statistic 0.896. most influential were identified SHAP values, FSS narrowing them down 12 critical effective WSM, evidenced by stabilized OA values (0.904 0.881, respectively). Further validation ninefold spatial cross-validation technique demonstrated method's consistent across data partitions, ranging 0.705 0.894 0.607 0.867. By providing more accurate comprehensible XAI-based research contributes broader field monitoring disaster response, underscoring analysis models' capabilities.

Language: Английский

---

Spatio-temporal patterns of the construction and development of urban open spaces in Macau from 1889–2020

Journal of Asian Architecture and Building Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 23

Published: Jan. 30, 2025

This study investigates the spatiotemporal evolution of urban open spaces in Macau from 1889 to 2020, aiming uncover historical progression Macau's landscape. The research hypothesizes that space development is inversely related its socio-economic advancement, with a notable shift abundant increased built-up areas. Utilizing ArcGIS software for spatial analysis and mapping, calculates proportion areas across different periods, revealing high initial declined economic modernization density. originality lies comprehensive patterns, focusing on unique typology "Largo" spaces, which are integral form cultural identity. provides these tracing their traditional European plaza concepts multifunctional accommodate dense living. research's practicality demonstrated through recommendations future planning Macau. It suggests balanced approach includes preservation revitalization Largo also emphasizes importance community engagement management ensuring they meet needs residents reflect local values. By examining current state, offers valuable insights similar ultra-high-density cities, providing model ecological construction sustainable planning. findings underscore necessity preserving green maintain well-being heritage

Language: Английский

---

Optimization of land-use pattern based on suitability and trade-offs between land development and protection: A case study of the Hohhot-Baotou-Ordos (HBO) area in Inner Mongolia, China

Journal of Cleaner Production, Journal Year: 2024, Volume and Issue: 466, P. 142796 - 142796

Published: June 4, 2024

Language: Английский

---

Analyzing and Simulating the Influence of a Water Conveyance Project on Land Use Conditions in the Tarim River Region

Land, Journal Year: 2023, Volume and Issue: 12(11), P. 2073 - 2073

Published: Nov. 18, 2023

Arid and semi-arid areas are facing severe land degradation desertification due to water scarcity. To alleviate these environmental issues, the Chinese government has launched a “water conveyance” project for protection along Tarim River. While previous studies have mainly focused on conditions, influence of policies use conditions remains less explored. Therefore, this study first simulated cover (LULC) changes in major city (Korla) around We found that conveyance routes exerted notable influences surrounding LULC changes. Next, we primarily among different reaches forest lower increased at expense slight decrease such upper middle reaches, which suggests policy may also unintended consequences. These findings could attract attention decision makers many other arid areas, they provide practical implications similar inter-basin projects. The benefits risks man-made projects should be carefully balanced.

Language: Английский

---

Investigating the Spatial Distribution and Influencing Factors of Non-Grain Production of Farmland in South China Based on MaxEnt Modeling and Multisource Earth Observation Data

Foods, Journal Year: 2024, Volume and Issue: 13(21), P. 3385 - 3385

Published: Oct. 24, 2024

Excessive non-grain production of farmland (NGPF) seriously affects food security and hinders progress toward Sustainable Development Goal 2 (Zero Hunger). Understanding the spatial distribution influencing factors NGPF is essential for agricultural management. However, previous studies on identification have mainly relied high-cost methods (e.g., visual interpretation). Furthermore, common machine learning techniques difficulty in accurately identifying based solely spectral information, as not merely a natural phenomenon. Accurately at grid scale elucidating its emerged critical scientific challenges current literature. Therefore, aims this study are to develop grid-scale method that integrates multisource remote sensing data enhance precision provide more comprehensive understanding factors. To overcome these challenges, we combined images, natural/anthropogenic factors, maximum entropy model reveal scale. This combination can detailed information quantify integrated influences multiple from microscale perspective. In case Foshan, China, area under receiver operating characteristic curve 0.786, with results differing by only 1.74% statistical yearbook results, demonstrating reliability method. Additionally, total error our result lower than using information. Our enhances resolution effectively detects small fragmented farmlands. We identified elevation, farming radius, population density dominant affecting NGPF. These offer targeted strategies mitigate excessive The advantage lies independence negative samples. feature applicability other cases, particularly regions lacking high-resolution grain crop-related data.

Language: Английский

---

How to Synergize Natural Resource Supply-Demand Mismatching to Allocate the Most Suitable Nbs Measures?

Published: Jan. 1, 2025

The application of Nature-based Solutions (NbS) measures can improve the ability natural resources supply, providing material basis for necessary guarantees sustainable development. However, there is frequently a lack scientific decision-making that incorporates local and social needs when planning NbS measures. In response to different types provide variety resource supply remedies, this study proposed methodology which applied Yangtze River Economic Belt (YREB) in China, considering four major five elements, are assigned steps according "where-what-how" framework. results showed indicative sites implementation distributed three parallel stripes pattern across area, among them, water food were two most needed covering up 80% area area. Combined with estimated 2030, socio-climatic development pathways lead changes prioritized exported by sites. Our approach be used plan decisions multiple compensation capacity where it needed.

Language: Английский

---

Modeling Susceptibility to Illegal Land Occupation in Cape Town, South Africa: A Random Forest Approach

Transactions in GIS, Journal Year: 2025, Volume and Issue: 29(1)

Published: Feb. 1, 2025

ABSTRACT Illegal land occupation is a pervasive challenge in South Africa, particularly urban landscapes such as Cape Town. Despite numerous studies investigating its causes, spatial distribution, and impacts, there scarcity of research focused on predicting occurrence. This study addresses this gap by developing machine learning model to identify areas susceptible illegal invasion within the Town Metropole. A random forest (RF) regression was built utilizing samples prevalence pseudoabsence. total 1070 were collected (535 points per class), with 70% used for training 30% validation. The RF demonstrated accurate predictive performance an R 2 0.809. study's findings indicate that bordering existing informal settlements are most at risk future occupation. developed can be valuable tool planners policymakers more effective strategies prevent manage

Language: Английский

---

Grid-Scale Poverty Assessment by Integrating High-Resolution Nighttime Light and Spatial Big Data—A Case Study in the Pearl River Delta

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(18), P. 4618 - 4618

Published: Sept. 20, 2023

Poverty is a social issue of global concern. Although socioeconomic indicators can easily reflect poverty status, the coarse statistical scales and poor timeliness have limited their applications. While spatial big data with reasonable timeliness, easy access, wide coverage overcome such limitations, integration high-resolution nighttime light for assessing relative still limited. More importantly, few studies provided assessment results at grid scale. Therefore, this study takes Pearl River Delta, where there large disparity between rich poor, as an example. We integrated Luojia 1-01, points interest, housing prices to construct index (BDPI). To evaluate performance BDPI, we compared new traditional multidimensional (MPI), which builds upon indicators. The show that impoverished counties identified by BDPI are highly similar those MPI. In addition, both MPI gradually decrease from center fringe area. These two methods indicate were mainly distributed in ZhaoQing, JiangMen HuiZhou Cities, while also several parts rapidly developing cities, CongHua HuaDu Counties GuangZhou City. difference suggests effectively reveal status old urban areas convenient but obsolete infrastructures, whereas suitable emerging-development lagging behind. share calculation procedures, substantial differences meaning suitability methodology. lacking accurate statistics, replace achieve timely fine-scale assessment. Our proposed method could provide reliable reference formulating targeted poverty-alleviation policies.

Language: Английский

---

Land subdivision in the law's shadow: Unraveling the drivers and spatial patterns of land subdivision with geospatial analysis and machine learning techniques in complex landscapes

Landscape and Urban Planning, Journal Year: 2024, Volume and Issue: 249, P. 105106 - 105106

Published: May 14, 2024

Language: Английский

---