Sustainable Development Decisions Research Articles

The Water Resources Rebound Effect Threatening the Achievement of Sustainable Development Goal 6 (SDG 6)

Coaction of climate change and human activities exerts a significant impact on the fate of water resources, provoking the rebound effect in water resources and threatening the achievement of SDG (sustainable development goal) 6. However, the mechanisms of interactions between this effect and SDG 6 and how to decrease this effect towards the achievement of SDG 6 are less known. In this paper, a water resources rebound effect (WRRE) model is integrated into a river basin sustainable development decision support system to simulate and project the interactions between the WRRE and SDG 6 under multiple combination scenarios. The results show that multiple drivers, including precipitation, technological advances, and ecological water flow, coaffect the WRRE, not the silo technology factor. The transfer fate of the saved water is a major root cause leading to the WRRE and harming the achievement of SDG 6, and the WRRE is positively correlated to SDG 6 overall, which, nevertheless, can sometimes be reversed by technological advances. Our outcomes indicate that decoupling SDG 6 from the WRRE can promote the achievement of SDG 6 and decrease the rebound effect, relying on holistic integration that couples climatic, socioeconomic, and behavioral interaction between SDG 6 and the WRRE and translation of scientific research into available decision-making information for strict scientific-research-based policy actions.

Some modeling challenges in dynamic life cycle assessment

Life cycle assessment (LCA) has been a mainstream tool to evaluate the environmental impacts of products, services, and systems. Current LCAs inherently rely on the static basis and commonly fail to include temporal considerations. To better assist in the decision-making for sustainable development, dynamic LCA has been initiated to answer more complex and interdisciplinary questions. As in its initial phase, dynamic LCA faces many modeling challenges that at the same time are meaningful research opportunities. In modeling dynamic LCA, there are several key aspects that need more attention for contribution and close collaboration across the first three phases of the LCA framework.

The influence of gender specific decisions on household technology choice within the farming households in central Uganda

How households make decisions, who influences decision making and how members bargain over resources and opportunities greatly affects the livelihood and wellbeing of members within a given household. This study sought to understand gender specific decisions and their influence on household technology choice, packaging and adoption of agricultural technologies. Growing Bananas with Trees and Livestock (GBTL) technology system was implemented by National Agricultural Research Organisation and Bioversity International in three districts of Central Uganda: Kiboga, Nakaseke and Ssembabule. Using Principal Component Analysis (PCA) and Cluster Analysis (CA), typologies were created in which two distinct clusters of farming households were revealed. Using a bargaining model of technology adoption, three types of households were identified; male and female only, female only and male only headed households. For technology uptake, either a single component, two components or all components of a technology was adopted. Results indicated that Household size, age, land owned, labour and gender composition of the household positively influenced the adoption of the technology. Farm households were able to take up and adopt components of the technology that were equivalent to the available household resources. Technology choice and adoption was influenced by available land, labor and household objectives (food, income and nutrition security). Households' ability to avert the loss of production and/or assets was very varied and depended on household size. For non-business home expenses, decisions followed a gendered perspective where households with both male and female, had more participants involved in household decision making, households make decision jointly when it comes to purchases and sales. Banana plantations establishment and management was for the spouse. Livestock production was initiated and managed by the household heads. Individual decisions were influenced by age of the household head, livestock owner. Joint household’s decision making was significant on purchases, sales of inputs and outputs, land ownership, and were influenced by household size and farm size. This study brings out important policy implications that in order to ensure widespread adoption of improved technologies, there should be equitable access to complementary inputs, especially land and labour for females. And technology packaging should take into consideration the gender specific decisions for sustainable agricultural development. Key words: Decision making, Technology choice, adoption, Coffee banana farming system, Gender

Semantic segmentation of urban environments: Leveraging U-Net deep learning model for cityscape image analysis.

Semantic segmentation of cityscapes via deep learning is an essential and game-changing research topic that offers a more nuanced comprehension of urban landscapes. Deep learning techniques tackle urban complexity and diversity, which unlocks a broad range of applications. These include urban planning, transportation management, autonomous driving, and smart city efforts. Through rich context and insights, semantic segmentation helps decision-makers and stakeholders make educated decisions for sustainable and effective urban development. This study investigates an in-depth exploration of cityscape image segmentation using the U-Net deep learning model. The proposed U-Net architecture comprises an encoder and decoder structure. The encoder uses convolutional layers and down sampling to extract hierarchical information from input images. Each down sample step reduces spatial dimensions, and increases feature depth, aiding context acquisition. Batch normalization and dropout layers stabilize models and prevent overfitting during encoding. The decoder reconstructs higher-resolution feature maps using "UpSampling2D" layers. Through extensive experimentation and evaluation of the Cityscapes dataset, this study demonstrates the effectiveness of the U-Net model in achieving state-of-the-art results in image segmentation. The results clearly shown that, the proposed model has high accuracy, mean IOU and mean DICE compared to existing models.

Contributions of the IUCN Red List of Ecosystems to risk-based design and management of protected and conserved areas in Africa.

Protected and conserved areas (PCAs) are key ecosystem management tools for conserving biodiversity and sustaining ecosystem services and social cobenefits. As countries adopt a 30% target for protection of land and sea under the Global Biodiversity Framework of the United Nations Convention on Biological Diversity, a critical question emerging is, which 30%? A risk-based answer to this question is that the 30% that returns the greatest reductions in risks of species extinction and ecosystem collapse should be protected. The International Union for Conservation of Nature (IUCN) Red List protocols provide practical methods for assessing these risks. All species, including humans, depend on the integrity of ecosystems for their well-being and survival. Africa is strategically important for ecosystem management due to convergence of high ecosystem diversity, intense pressures, and high levels of human dependency on nature. We reviewed the outcomes (e.g., applications of ecosystem red-list assessments to protected-area design, conservation planning, and management) of a symposium at the inaugural African Protected Areas Congress convened to discuss roles of the IUCN Red List of Ecosystems in the design and management of PCAs. Recent progress was made in ecosystem assessment, with 920 ecosystem types assessed against the IUCN Red List criteria across 21 countries. Although these ecosystems spanned a diversity of environments across the continent, the greatest thematic gaps were for freshwater, marine, and subterranean realms, and large geographic gaps existed in North Africa and parts of West and East Africa. Assessment projects were implemented by a diverse community of government agencies, nongovernmental organizations, and researchers. The assessments have influenced policy and management by informing extensions to and management of formal protected area networks supporting decision-making for sustainable development, and informing ecosystem conservation and threat abatement within boundaries of PCAs and in surrounding landscapes and seascapes. We recommend further integration of risk assessments in environmental policy and enhanced investment in ecosystem red-list assessment to fill current gaps.

Potential thermal constraints for sustainable industrial city: refined simulation and prediction of extreme urban heat island effect

Extreme urban heat islands (E-UHIs) have caused radical changes in urban climates. The lack of refined extreme thermal environment simulation models (ETESM) hinders research on the spatial evolution of E-UHI, which increases the uncertainty for managers to make sustainable decisions. Here, considering both the heating of industrial land and the heat transfer of surrounding facilities, a refined ETESM is constructed. Assuming four scenarios: maintain current trend (MtS), economically oriented scenario (EcS), environmentally oriented scenario (EnS), green transformation scenario (GtS), the future potential constraints of the E-UHI are simulated and predicted, thus determining the sustainable development decision in industrial city. The results indicate that there is significant spatial consistency between simulated temperature and actual temperature at both city scale (Pearson'r = 0.924, P<0.001) and industrial land scale (Pearson'r = 0.948, P<0.001). The average temperature under four scenarios shows: EcS>MtS>GtS>EnS. The average SST of EnS and GtS was 1.36℃ and 1.06℃ lower than that of MtS, respectively. Considering the dual constraints of environmental livability and economic sustainability, GtS is the best decision to achieve the sustainable development in industrial city. This simulation-driven study provides support for E-UHI mitigation and sustainable development of industrial city.

Integrated Reporting and Group Decision-Making for Sustainable Development: A Bibliometric Review

The demands of society are constantly evolving, imposing significant pressures on business organizations within the context of sustainable development policy. As a result, organizations have begun to move towards promoting information disclosure through integrated reporting, transitioning from sustainability reports to financial reports. Simultaneously, decisions made to address specific problems are no longer the sole responsibility of a single individual. Challenges now revolve around group decision-making with the aim of achieving a consensus solution. To comprehend the landscape of integrated reporting and group decision-making in the scientific literature concerning sustainable development, a bibliometric review was conducted across major scientific databases from 2008 to 2023. The analysis utilized Bibliometrix, based on the R language, and Biblioshiny for graphic generation. The results indicate a quantitative increase in publications addressing integrated reporting and group decision-making in the context of sustainable development. However, a thematic isolation among existing studies was evident, pointing to an opportunity for future research to bridge the gap and establish more robust connections between the subjects. &#x0D; Keywords: integrated reporting, group decision-making, sustainable development, bibliometric review&#x0D;

Interplay of network information dissemination in the era of big data on environmental sustainable development and agricultural consumers' purchase decisions

The rapid progress of technology has led to a proliferation of information sources and distribution channels, facilitating the dissemination of knowledge on environmental sustainability and agricultural practices to consumers. However, the intricate impact of Network Information Dissemination (NID) on environmental sustainability and consumer purchasing decisions in agriculture remains a complex area of study. This research aims to explore the interconnections between network information dissemination, environmental sustainability, agricultural consumer purchase decisions, and the mediating role of information overload and trust in information sources. Additionally, it investigates the moderating impact of information accessibility. Employing a quantitative research design, data is collected through an online survey targeted at Chinese consumers, with 400 responses being evaluated using SmartPLS. The findings reveal that network information distribution significantly and positively influences both environmental sustainability and agricultural consumer purchasing decisions. Moreover, the study identifies that information overload and trust in information sources act as moderators in the relationship between network information diffusion and agricultural consumer purchasing decisions. Additionally, the research indicates that information accessibility moderates the relationship between network information distribution and environmental sustainability. Specifically, when information accessibility is high, the relationship is more pronounced compared to situations where accessibility is low. This underscores the importance of information accessibility in achieving environmental sustainability through network information transmission.

INTEGRATED REPORTING QUALITY DETERMINANTS: THE CASE OF BASIC MATERIALS AND INDUSTRIAL COMPANIES

This study investigates the determinants of integrated reporting quality in the context of basic materials and industrial companies. The motivation stems from the need to enhance reporting quality and provide guidance to companies and academia. Specific hypotheses were formulated, including the influence of profitability, company size, age, and board size on integrated reporting quality. The research aims to offer insights into these factors' impact. The study employs a mixed-method approach involving quantitative regression analysis and qualitative content analysis. Findings reveal that profitability is not a significant determinant of integrated reporting quality, while larger companies exhibit higher-quality reports. Younger firms tend to present more elaborate reports. The study validates the role of board size in enhancing reporting quality. These results contribute to refining integrated reporting standards, enhancing transparency, and guiding strategic decisions for sustainable development.

Mapping and Analyzing the Spatiotemporal Patterns and Drivers of Multiple Ecosystem Services: A Case Study in the Yangtze and Yellow River Basins

The Yangtze River Basin (YZRB) and the Yellow River Basin (YRB), which are crucial for ecology and economy in China, face growing challenges to ecosystem service (ES) functions due to global population growth, urbanization, and climate change. This study assessed the spatiotemporal dynamics of ESs in the YZRB and the YRB between 2001 and 2021, comprehensively encompassing essential aspects such as water yield (WY), carbon sequestration (CS), soil conservation (SC), and habitat quality (HQ) while also analyzing the trade-offs and synergies among these ESs at the grid cells. The GeoDetector was employed to ascertain individual or interactive effects of natural and anthropogenic factors on these ESs and their trade-offs/synergies. The results showed that (1) from 2001 to 2021, the four ESs exhibited significant spatial disparities in the distribution within two basins, with the overall trend of ESs mainly increasing. YZRB consistently exhibited substantially higher ES values than the YRB. (2) Complex trade-offs and synergies among these ESs were apparent in both basins, characterized by distinct spatial heterogeneity. The spatial relationships of WY–CS, WY–SC, CS–SC, and CS–HQ were mainly synergistic. (3) Precipitation, potential evapotranspiration, elevation, land use and land cover (LULC), and slope influenced ESs in both basins. Notably, interactive factors, particularly the interactions involving LULC and other factors, demonstrated more robust explanatory power for ESs and their trade-offs/synergies than individual drivers. These findings significantly affect the refined ecosystem management and sustainable development decision-making in large rivers or regions.

Sustainable decision making based on systems integration and decision support system promoting endorheic basin sustainability

Sustainability has become a target in official policy rhetoric. However, the gap between scientific investigation and practical decision-making poses a significant challenge in achieving sustainability, particularly in endorheic regions. Addressing this challenge requires the translation of scientific outcomes into available decision-making information. In this study, we propose a sustainable decision-making methodology, namely, decision rehearsal, that has four stages: the scientification of decision-making problems, the politicization of scientific knowledge, the translation of scientific findings into decision-making information, and the translation of decision-making information into policy action. Based on this theoretical framework, an ensemble artifact, referred to as the River Basin Sustainable Development Decision Support System (RSDSS), was designed, built and evaluated from a design science research perspective to address a class of sustainability problems in endorheic basins. This system integrates a watershed-integrated model, disaggregated sustainable development goals (SDGs), localized shared socioeconomic pathways (SSPs), and a sustainability assessment model, which can assist decision- and policy-makers in more deeply understand the impacts of different policy assumptions on the interactions between human and natural systems and watershed sustainability. Some related RSDSS cases are discussed to demonstrate the ability of the RSDSS to resolve complex watershed problems, which implies that the RSDSS can promote sustainable river basin management.

Quantitative Study of Post-Pandemic Electricity Productivity Fluctuations Based on LMDI

This study focuses on China's electricity productivity post-pandemic, employing the Logarithmic Mean Divisia Index (LMDI) method and the Kaya identity. Despite the clarity of the electricity productivity indicator, factors like industrial structure, energy efficiency, and electrification rates contribute to fluctuations. Quantitative analysis reveals a decisive role of the terminal electrification rate in declining electricity productivity. The proposed analytical method provides a more accurate assessment of electricity's contribution to economic growth, aiding informed policy decisions for sustainable energy development in China.

Late Quaternary palaeoclimatic records from the Indian Himalaya and Ganga foreland basin: Assessment on current understanding and future prospective

In this comprehensive review, an extensive analysis has been conducted on paleoclimate datasets from climatically sensitive regions in the Indian Himalaya and Indo-Gangetic plain. Our main objective was to gain valuable insights into the broad palaeoclimatic variability during the Late Quaternary-Holocene period. To achieve this, careful categorization was focused for various archives from multi-proxy studies into three groups: glacial moraine, glacio-fluvial and lake records, and speleothems. The compilation of climate records from different geographical settings has revealed an overall coherence during warm and humid phases, with minor variations influenced by variable moisture sources and topographic changes. The analysis reveals that Indian Summer Monsoon (ISM) reached its peak during approximately 9-5 ka BP and subsequently weakened around the Mid-Holocene (ca. 4–5 ka BP). Notably, the Last Glacial Maximum (LGM) and early Holocene were characterized by significant glacial advances in the Himalayan region. Furthermore, the sedimentation rates derived from lacustrine records in different regions exhibit considerable variability. In conclusion, the compilation and comparisons of diverse palaeoclimate records have significantly improved our understanding of the regions palaeoclimate. These findings hold substantial value for planning future focused studies in the crucial climatic zone. By refining our understanding of past climate dynamics in the Indian Himalaya and Indo-Gangetic alluvium, a better comprehension of the regions susceptibility to climate change can be achieved. This, in turn, facilitates informed decisions for sustainable development and environmental management.

Green Supplier Assessment and Selection for Sea Cucumber (Apostichopus japonicus) Processing Enterprise: Case Study in China

Green supply chain management is a crucial way to balance economic benefits and environmental impacts. As an important economic aquatic product in China, sea cucumber (Apostichopus japonicus) is facing the dual challenges of economic benefits (profit) and environmental sustainability (material input and emission output). Currently, the sea cucumber industry in China lacks a green supplier screening system, resulting in a fragmented pattern of cooperation among enterprises. Core enterprises in the supply chain cannot assume social responsibility to help and guide upstream and downstream enterprises to jointly improve environmental performance. This study focuses on the selection and evaluation of green suppliers for sea cucumber processing enterprises. Firstly, a green supplier assessment indicator system for sea cucumber processing enterprises was established, and the indicator weights were determined by the analytic hierarchy process (AHP) method. Next taking a large sea cucumber processing enterprise in Dalian, China, as an example, the importance level of each index was evaluated by fuzzy comprehensive evaluation (FCE), and the score and ranking of existing suppliers were determined. The validity and practicality of the method were verified. The results show that Supplier 1 (S1) has the highest score, and the price of sea cucumber farming, the cleaner production level of sea cucumber farming, environmental awareness, and long-term cooperation willingness were the most important factors in the selection of green suppliers for sea cucumber processing enterprises, which provides useful clues on the best practice of making sustainable development decisions. With an in-depth understanding of the key factors, suppliers can formulate different prices according to the differences in sales channels to improve the economic deficiencies. Environmental pollution can also be reduced by using clean energy, establishing a recirculating aquaculture system, and using micro-ecological preparations. The conclusions of this study can provide technical support and decision-making suggestions for the application of green supply chain management in China’s aquaculture industry.

Assessing ESG Factors and Policies of Green Finance Investment Decisions for Sustainable Development in China Using the Fuzzy AHP and Fuzzy DEMATEL

China has become more aware of the negative environmental impact caused by its economic expansion and fast-paced development. Therefore, the country mainly focuses on sustainable development and green finance. To evaluate the environmental, social, and governance (ESG) factors and policy options for green finance investment decisions in China, the fuzzy analytical hierarchy process (AHP) and fuzzy decision-making trial and evaluation laboratory (DEMATEL) techniques are employed. The fuzzy AHP method identifies and analyzes the most significant ESG factors and sub-sub-factors to comprehensively understand sustainable investment in China. Furthermore, this study uses the fuzzy DEMATEL method to prioritize the main policy options for advancing sustainable development and green finance investment decisions in China. The fuzzy AHP method shows that the environmental factor (ESG1) is the most significant factor for green finance investment decisions in China, followed by the governance (ESG3) and social factors (ESG2). The fuzzy DEMATEL method results revealed that supporting green finance innovation and development (P1) is the highest priority, followed by encouraging social responsibility and community engagement (P4) and developing and enforcing environmental regulations (P2). The study’s findings will significantly benefit investors and decision-makers who wish to promote sustainable development and make decisions regarding green financing. The study recommends that investors and policy makers concentrate their resources and efforts on the most crucial ESG factors and policies to build sustainability and resilience in the country.

An analysis of the dynamics of land surface temperature on land use/ land cover in Kano Metropolis, Kano State, Nigeria

The rapid urbanisation and associated land use changes have profound impacts on the local climate and environmental conditions in urban areas. This study aims to analyse the dynamics of land surface temperature (LST) and its relationship with land use/land cover (LULC) patterns in Kano Metropolis, Kano State, Nigeria. The research utilizes remote sensing data and geospatial techniques from multiple sensors, such as Landsat MSS, ETM + and OLI/TIRS, spanning a period of 38years (1984 – 2022), to processed, analysed and investigate the spatiotemporal variations in LST and their drivers. Statistical analyses, such as correlation and regression models, are employed to quantify the associations between LST and LULC variables. Findings show that urban area increased from 7% in 1984 to 32% in 2022, while bare land decreased from 82% in 1984 to 49% in 2022. Vegetation also increased slightly from 11% in 1984 to 19% in 2022. The LST increased with a mean value of 16°C in 1984, 25°C in 2003, and 30.5°C in 2022. Results still revealed a negative correlation between vegetation health and land surface temperature, indicating that as vegetation health declines, land surface temperature increases due to the lack of cooling effects from transpiration while a positive correlation exist between the built-up index and land surface temperature, signifying that as urban areas expand, land surface temperature rises due to the urban heat island effect. The research emphasises the significance of implementing land use planning and management strategies to address the adverse effects of urban heat and improve the urban microclimate. The findings offer valuable guidance for policymakers, urban planners, and environmental practitioners, assisting them in making informed decisions for sustainable urban development and enhancing the residents' quality of life in Kano Metropolis.

Spatial heterogeneity characteristics and driving mechanism of land use change in Henan Province, China

We conducted a scientific quantitative analysis of the spatiotemporal evolution and driving factors of land use in Henan Province using a spatial zoning approach. The province was divided into five distinctive regions. Employing methods, such as information mapping, we analyzed land use data for 1990, 2000, 2010, and 2020, investigating spatiotemporal evolution and differences. Additionally, we employed a geographic detector model to explore the dominant factors behind land use changes in 2010 and 2020. Primary land classes in Henan Province included cultivated land, forests, and construction, with cultivated land transitioning mainly to forests and construction. However, regional analyses revealed diverse outcomes. In the Yudong area, cultivated land dominated with an 80% area proportion, shifting mostly to construction. In the Yubei area, grassland transformed into cultivated land and forests, with escalating grassland loss. The Yuxi area exhibited a 40% forest area proportion, with frequent mutual conversions between forests, cultivated land, and grassland. Spatiotemporal evolution indicated active changes in cultivated land. The geographic detector revealed a shift in influential factors from natural to economic drivers for cultivated land changes in Henan Province between 2010 and 2020. By uncovering land use disparities across regions, we contribute suggestions for sustainable development decisions regarding land use in Henan.

Habitat quality assessment and multi-scenario prediction of the Gansu-Qinghai section of the Yellow River Basin based on the FLUS-InVEST model

Research on the impact of land use change on regional habitat quality, in various future scenarios, can effectively aid planning and decision-making for sustainable development at a regional level. The study conducted its research in the Gansu-Qinghai Yellow River section and used ArcGIS and a land use transfer matrix to analyze the spatiotemporal pattern of land use and land cover changes. The study assessed the changes in habitat quality in the Gansu-Qinghai Yellow River region between 1990 and 2020, using the Integrated Valuation of Ecosystem Services and Trade-offs (InVEST) model, by evaluating the gains and losses. Simultaneously, 15 elements of the natural economy were chosen and examined for their temporal and spatial impact on habitat quality using the random forest model and spatially weighted regression model. To forecast land use changes in the Gansu-Qinghai Yellow River section for 2030, the Future Land Use Simulation Model (FLUS) model was utilized and a series of four scenarios (cultivated land protection scenario, ecological protection scenario, natural development scenario, and rapid development scenario) were employed. The research results indicate that over 70% of the Gansu-Qinghai Yellow River is occupied by grasslands, and only a small portion of the area, about 0.22%, is developed for construction purposes. The quality of the habitat in the Gansu-Qinghai Yellow River had a minor drop between 1990 and 2020, followed by an improvement. Habitat quality changes are primarily attributed to improvements, with variations across different areas, i.e., enhanced in the east and reduced in the central and western parts. The habitat quality of the Gansu-Qinghai Yellow River has improved in all four scenarios compared to 2020, as evidenced by the decrease in low-value habitats and increase in high-value areas. The ecological protection scenario has the highest average habitat quality value. These research results can be used to support policy development and ecological restoration initiatives in the Gansu-Qinghai Yellow River.

Group assessment for the selection of sustainable small-scale power supply projects: A study case from northern Colombia

Sustainability assessment provides essential information to facilitate informed decision-making, enabling the selecting of the best option among various projects. This research paper considers the decision-making problem in the context of marginalised and isolated communities, introducing a groupal model for evaluating the sustainability of small-scale power supply projects. The proposed model incorporates a comprehensive set of five indicators and 25 criteria. The analysis presented in this study prioritises these indicators and criteria, introducing new criteria based on several stakeholders’ participation and offering guidance on measuring the identified criteria. Furthermore, the proposal provides fundamental thresholds for evaluating the projects’ sustainability and proposes a model based on aggregated indicators to assess the available alternatives. It encompasses all stages of the decision-making process, employing multiple indicators to evaluate the sustainability of power supply projects. The effectiveness of the proposed model was validated in a real case study conducted in a marginalised community facing isolation challenges in La Guajira, Colombia. The evaluation showcased the model’s contribution to decision-making processes regarding power supply projects in isolated communities. Finally, the results demonstrated the suitability of this strategy for immediate application, highlighting its potential impact on decision-making for sustainable development within marginalised areas.

Vegetation EVI changes and response to natural factors and human activities based on geographically and temporally weighted regression

The research on vegetation changes plays a crucial role in the assessment of ecosystem health, monitoring environmental changes, providing early warnings for natural disasters, and supporting decision-making for sustainable development. However, understanding the nonstationary characteristics of drivers affecting vegetation change remains challenging. This study used Enhanced Vegetation Index (EVI) data obtained through Google Earth Engine (GEE), Theil-Sen, and Mann-Kendall methods to analyze the spatial-temporal patterns and trends of vegetation changes in Sichuan, western China from 2000 to 2020. The Geographical and Temporal Weighted Regression (GTWR) method was applied to deal with spatial and temporal nonstationarity simultaneously. Results showed that vegetation cover in Sichuan was good overall, with medium and high vegetation covering more than 78% of the area. About 72.75% of the area showed an increasing trend in vegetation cover, and areas with extremely significant and significant EVI growth (p < 0.01 and 0.01 ≤ p < 0.05) accounted for 23.94% of the total area. The areas with significant increases in vegetation EVI were mainly distributed in northeast, east, southeast, central, and southwest in Sichuan, while the areas with significant decreases were mainly distributed in the central Sichuan plain urban agglomeration and western Sichuan plateau. GTWR addressed the nonstationary effect of the temporal dimension on the drivers of natural and human activities, with a fitted R2 of 0.846. The study identified climate, terrain, and human activities as the primary driving factors behind vegetation EVI fluctuations. Annual average temperature and precipitation, human activities, and slope had a positive impact on vegetation EVI changes, while solar radiation and aspect had a negative inhibitory effect. The effects of climate, terrain, and human activities on EVI changes exhibited significant spatial heterogeneity and clustering, resulting in either positive promotion or negative inhibition. This study provides an additional methodology to solve the nonstationary problem of vegetation change trends and their response mechanisms. The revealed changes in vegetation EVI and the spatiotemporal heterogeneity characteristics of their driving factors are important for fragile ecosystems to adapt to and mitigate the effects of natural changes and human activities. Revealing the variations in vegetation EVI and their underlying drivers can showcase diverse characteristics across regions and time periods, the presence of spatiotemporal heterogeneity holds great significance in comprehending the adaptive strategies employed by fragile ecosystems to mitigate the effects of natural fluctuations and human-induced activities.