Farm households in developing countries are often involved in a variety of livelihood income-generating activities to achieve basic needs and enhance food security. However, little attention has been given to investigating the effect of livelihood diversification strategies on the adoption of agricultural land management practices. This study explored the nexus between livelihood diversification and Agricultural Land Management (ALM) practices in the Southern Ethiopian Highlands. Data for this study were gathered through a structured questionnaire, interviews, and focus group discussions. A total of 423 sample respondents were selected by using multistage random sampling techniques. The data were analyzed using the Inverse Herfindahl Hirschman Diversity Index (IHHDI), the multinomial logit model (MNL), and the probit regression model. The findings of the study revealed that on-farm income activities are the most dominant livelihood income strategies (69.1%), followed by non-farm (21%) and off-farm (9.64%). The multinomial logit model analysis demonstrated that variables such as sex, education, family size, distance to market, land size, extension contact, membership in cooperatives, and household income were the major drivers of farmers income diversification activities (p<0.05). The results of the probit analysis indicated that income from crop production, daily labor work, rents from farmland, and farm assets have a positive and significant effect on households' decisions to implement ALM practices. In contrast, incomes from remittance and migrant sources have a negative but statistically significant impact on the adoption of ALM measures. The farm household sources of income-generating strategies substantially affected the adoption intensity of ALM measures. Income generated from the on-farm sector alone cannot be considered a core income-generating activity for households or a means of achieving food security. Therefore, land management policies and program implementations should consider farmers’ livelihood diversification and income-generating strategies. In addition, such interventions need to promote sustainable farming practices, enhance innovation, and related measures for the adoption of ALM measures to ensure land sustainability.

The destructive geohazard of landslides produces significant economic and environmental damages and social effects. State-of-the-art advances in landslide detection and monitoring are made possible through the integration of increased Earth Observation (EO) technologies and Deep Learning (DL) methods with traditional mapping methods. This assessment examines the EO and DL union for landslide detection by summarizing knowledge from more than 500 scholarly works. The research included examinations of studies that combined satellite remote sensing information, including Synthetic Aperture Radar (SAR) and multispectral imaging, with up-to-date Deep Learning models, particularly Convolutional Neural Networks (CNNs) and their U-Net versions. The research categorizes the examined studies into groups based on their methodological development, spatial extent, and validation techniques. Real-time EO data monitoring capabilities become more extensive through their use, but DL models perform automated feature recognition, which enhances accuracy in detection tasks. The research faces three critical problems: the deficiency of training data quantity for building stable models, the need to improve understanding of AI's predictions, and its capacity to function across diverse geographical landscapes. We introduce a combined approach that uses multi-source EO data alongside DL models incorporating physical laws to improve the evaluation and transferability between different platforms. Incorporating explainable AI (XAI) technology and active learning methods reduces the uninterpretable aspects of deep learning models, thereby improving the trustworthiness of automated landslide maps. The review highlights the need for a common agreement on datasets, benchmark standards, and interdisciplinary team efforts to advance the research topic. Research efforts in the future must combine semi-supervised learning approaches with synthetic data creation and real-time hazardous event predictions to optimise EO-DL framework deployments regarding landslide danger management. This study integrates EO and AI analysis methods to develop future landslide surveillance systems that aid in reducing disasters amid the current acceleration of climate change.

Mangrove forests are vital to coastal protection, biodiversity support, and climate regulation. In the Niger Delta, these ecosystems are increasingly threatened by oil spill incidents linked to intensive petroleum activities. This study investigates the extent of mangrove degradation between 1986 and 2022 in the lower Niger Delta, specifically the region between the San Bartolomeo and Imo Rivers, using remote sensing and machine learning. Landsat 5 TM (1986) and Landsat 8 OLI (2022) imagery were classified using the Support Vector Machine (SVM) algorithm. Classification accuracy was high, with overall accuracies of 98% (1986) and 99% (2022) and Kappa coefficients of 0.97 and 0.98. Healthy mangrove cover declined from 2804.37 km2 (58%) to 2509.18 km2 (52%), while degraded mangroves increased from 72.03 km2 (1%) to 327.35 km2 (7%), reflecting a 354.46% rise. Water bodies expanded by 101.17 km2 (5.61%), potentially due to dredging, erosion, and sea-level rise. Built-up areas declined from 131.85 km2 to 61.14 km2, possibly reflecting socio-environmental displacement. Statistical analyses, including Chi-square (χ2 = 1091.33, p < 0.001) and Kendall's Tau (τ = 1, p < 0.001), showed strong correlations between oil spills and mangrove degradation. From 2012 to 2022, over 21,914 barrels of oil were spilled, with only 38% recovered. Although paired t-tests and ANOVA results indicated no statistically significant changes at broad scales, localized ecological shifts remain severe. These findings highlight the urgent need for integrated environmental policies and restoration efforts to mitigate mangrove loss and enhance sustainability in the Niger Delta.

Land use as for human-circumstance interaction is as we all know changed the global land surface sharply and continuously. Farmland abandonment is the phenomenon of going extreme of marginal of land use, which exert positive and negative impacts on our living circumstances. In order to map the extent of farmland abandonment of Zhejiang Province, we try to use the geo-big data analysis platform to perform the massive data preprocessing and map the extent of farmland abandonment of the study area based on multi-source land use and land cover data. Then we execute landscape pattern analysis using landscape pattern analysis software and spatial auto-correlation (Moran's I) analysis based on ArcGIS and Fragstats software. We found that the area of farmland is about 16.32% on account of all land use types, which is 1.89104 km2. While the whole area of FA is 1.72 × 108 m2, and the farmland abandonment ratio is 1.65%. AF's area is about 1.95 × 109 m2, and the continuous cultivation ratio is 18.69%. The landscape fragmentation, landscape aggregation and landscape diversity of FA, AF and FL are different. At the same time, the spatial auto-correlation of FA and AF are dominant high congregation and low discrete. At last, we compared our calculated results with the existed research results which demonstrate our research does scientific convincible. We also make futural prospects prediction and show the research deficiency as well as bring out some policy implications based on our research, which means build proper land use management regulation and decrease the farmland abandonment on account of the premise of suitable land use policies.

In order to address severe siltation and enhance urban green spaces in Xianyang Lake, the research offers a sustainable solution by proposing an innovative integration of ecological dredging and landscape transformation. The key findings are as follows: Firstly, an ecological dredging mechanism was established by directly transporting sediment from Xianyang Lake to its central greenbelt, reducing dredging costs and environmental impact while creating a sustainable funding cycle through revenue from eco-tourism activities. Secondly, the landscape artistic conception of the central greenbelt was significantly improved by leveraging the natural distance between the lakeshore and the greenbelt, offering diverse viewing experiences and enhancing the cognitive abilities and urban life satisfaction of tourists. Thirdly, the project demonstrated substantial economic and social benefits, including revenue generation from paid activities like boat tours, increased public awareness of biodiversity through ecological education, and improved community well-being. The central greenbelt also enhanced the urban environment by improving air quality, mitigating the "heat island effect", and providing habitats for wildlife. This integrated approach serves as a model for sustainable urban development, offering valuable insights for cities facing similar ecological challenges. Future research should focus on long-term monitoring to further evaluate the ecological and socio-economic impacts of such projects.

Land use changes have been demonstrated to exert a significant influence on urban planning and sustainable development, particularly in regions undergoing rapid urbanization. Tehran Province, as the political and economic capital of Iran, has undergone substantial growth in recent decades. The present study employs sophisticated Geographic Information System (GIS) instruments and the Google Earth Engine (GEE) platform to comprehensively track and analyze land use change over the past two decades. A comprehensive analysis of Landsat images of the Tehran metropolitan area from 2003 to 2023 has yielded significant insights into the patterns of land use change. The methodology encompasses the utilization of GIS, GEE, and TerrSet techniques for image classification, accuracy assessment, and change detection. The Kappa coefficients for the maps obtained for 2016 and 2023 were 0.82 and 0.87 for four classes: built-up, vegetation cover, barren land, and water bodies. The findings suggest that, over the past two decades, Tehran Province has undergone a substantial decline in ecological and vegetative areas, amounting to 2.4% (458.3 km2). Concurrently, the urban area and the barren lands have expanded by 287.5 and 125.5 km2, respectively. The increase in water bodies during this period is likely attributable to the reduction of vegetation cover and dam construction in the region. The present study demonstrates that remote sensing and GIS are excellent tools for monitoring environmental and sustainable urban development in areas experiencing rapid urbanization and land use changes.