Rapid urbanization and population growth are major drivers of land use and land cover (LULC) change and can substantially alter ecological environmental quality (EEQ). This study assessed the spatiotemporal dynamics of LULC and their effect on EEQ in Rupandehi District, Nepal, over a 30-year period (1993–2023). Four ecological indicators representing greenness, wetness, dryness, and heat were derived from Landsat imagery in Google Earth Engine (GEE), and LULC was classified using a Support Vector Machine (SVM). The Remote Sensing Ecological Index (RSEI) was then constructed from these indicators using Principal Component Analysis (PCA) in ArcGIS Pro, and its spatial structure was examined using global and local spatial autocorrelation. The mean RSEI followed a non-linear trajectory, rising from 0.59 in 1993 to 0.635 in 2004, declining to 0.55 in 2013, and recovering to 0.67 in 2023, indicating an overall improvement in EEQ with a temporary mid-period decline. Over the same period, built-up areas expanded substantially and agricultural land declined, whereas forest cover fluctuated but showed a slight net increase by 2023, and barren land decreased markedly. Higher EEQ was concentrated in the forested northern hills, while lower values occurred in the urban centers of Butwal and Bhairahawa, closely matching the spatial pattern of LULC change. The results indicate that ecological quality reflects the combined influence of all land cover classes rather than any single class. This study provides a transferable and reproducible workflow for long-term ecological assessment based on openly available Landsat data, with the analysis code shared in a public repository, offering practical guidance for sustainable land management and environmentally responsible urban development.

Riparian land use and land cover (LULC) exerts scale- and season-dependent controls on surface water quality, yet its influence in regulated agricultural–urban rivers is poorly characterized. We combined seasonal t-tests, one-way ANOVA, and redundancy analysis (RDA) at three riparian buffer scales (500, 1000, and 2000 m) to examine discharge, dissolved oxygen (DO), temperature, turbidity, and pH at four USGS stations along the Kansas River mainstem (2019–2026). DO and temperature showed the strongest seasonal contrasts: DO was 3.1–3.7 mg/L higher in the dry season and temperature 13–15 °C higher in the wet season, a coupling central to aquatic habitat suitability. Turbidity rose significantly in the wet season, consistent with agricultural runoff and sediment mobilization, whereas discharge showed no significant seasonal difference at three of four stations, reflecting upstream reservoir regulation. Spatial ANOVA detected station-level differences only for wet-season DO ($F_{3,28}=4.91$, $p=0.007$), which was lowest at the downstream urbanized station. RDA linked agricultural cover to turbidity and urban cover to reduced wet-season DO, although permutation tests were non-significant ($p\ge 0.42$) at $n=4$ replicates. Seasonality and riparian LULC jointly shape water quality along this regulated river, and the 500 m buffer is the most spatially discriminating scale for land-cover assessment.

The evaluation of Eco-Environmental Quality (EEQ) is important to maintain the quality of ecology and is crucial for the protection of the environment and promote sustainable development. In the past 30 years, Rupandehi district has gone into rapid urbanization and population growth due to the migration of people causing drastic changes in Land use. This study takes Rupandehi district as a study area and analyses the land use change dynamics and its impact on the ecological environment from 1993 to 2023. The study utilizes the cloud computing capability of Google Earth Engine (GEE) to extract multiple indices using Landsat remote sensing data. We also applied the Thresholding approach to various spectral indices to extract land use information in GEE. The Remote Sensing Ecological Indices (RSEI) was constructed using Principal Component Analysis (PCA) to monitor the ecological quality and the effect of Land Use Land Cover (LULC) change on the quality of ecology was analysed. The result shows that the overall ecological quality of the Rupandehi district is good ranging from 0.59 in 1993 to 0.67 in 2023 with a significant impact of land use change. The eco-environmental quality of the study area is deteriorating because of a sharp increase in built-up areas and deforestation as well as the loss of agricultural land. Meanwhile, the spatial and temporal distribution of land use change collides with the change in the ecological quality of the study area. This study provides an accurate and rapid assessment of ecological quality and monitors the impact of land use change on it providing a scientific basis for researchers, government, and others to preserve the ecology and promote sustainable and eco-friendly development.

In Deep Learning Remote Sensing, data quantity is rarely the limiting factor. A single high-resolution satellite image can yield thousands of training patches. What determines model performance, yet remains largely overlooked, is the quality of those patches. To date, the choice of sampling method has rarely been treated as a methodological decision. Conventional approaches, namely sliding-window and random sampling, introduce two compounding data-quality problems: severe class imbalance caused by the overproduction of background-only patches and negative learning arising from incomplete annotations, where unlabeled objects are implicitly treated as negative examples during training. To address these limitations at the data construction stage, we propose object-centric patch sampling, a model-independent strategy that anchors each training patch to the geometric centroid of an annotated object. This design ensures that every object-anchored patch contains at least one target instance and substantially reduces exposure to unlabeled regions that generate false-negative supervision signals; only a small, deliberately controlled proportion of background-only patches is retained to preserve contextual variety without reinstating background dominance. The method is evaluated on three heterogeneous remote sensing datasets spanning satellite (Sentinel-2, 10 m), aerial (NAIP, 1 m), and UAV (0.25 m) imagery, covering cotton field segmentation, rural building extraction, and water body delineation, respectively. Using a U-Net architecture under identical training conditions, the proposed approach achieves IoU scores of 0.929, 0.896, and 0.912 on the three datasets, respectively, outperforming sliding-window sampling by up to 19.6 percentage points in IoU and consistently delivering higher F1-scores across all experimental configurations. Evaluation under DeepLabV3+ gives a mean IoU of 0.9504 and a mean F1-score of 0.9772 in a multi-class segmentation task, indicating that the gains are not specific to a single architecture. Unlike model-level solutions such as focal loss or class reweighting, the proposed method improves training data quality at its source and integrates seamlessly into any deep learning pipeline without architectural modifications.