Amchang occupies a precarious position in every sense. Declared a wildlife sanctuary in 2004, it sits on the southern bank of the Brahmaputra River, hemmed in by Guwahati’s sprawl to the west and rural agricultural land to the south and east. It forms part of the Indo-Burma biodiversity hotspot, one of only 34 such regions recognised worldwide, and shelters endangered species including the Asian elephant, the hoolock gibbon and the leopard. Its vegetation ranges from tropical moist deciduous and semi-evergreen forest to bamboo brakes and grassland, dominated by trees such as sal, teak and Terminalia species. Yet the sanctuary also carries a heavy burden of biological invasion: earlier surveys have recorded 57 invasive plant species from 22 families, with more than 47 percent of the total area invaded by the four most common invaders and roughly 27 percent of that invaded zone severely impacted.

To track three decades of change, the research team led by Trishna Changkakoti of The Assam Royal Global University assembled multi-temporal Landsat imagery at 30-metre resolution, drawing on Landsat 5 TM data from 1995, Landsat 7 ETM+ from 2005, and Landsat 8 OLI/TIRS data for 2015 and 2025. Images were selected from the dry season months of February and March to minimise cloud cover and phenological differences between years. All processing, from pre-processing through classification, was carried out in Google Earth Engine and ArcGIS 10.8, with radiometric correction converting raw digital numbers into surface reflectance values so that the multi-temporal datasets could be compared consistently. The team then layered in three spectral indices designed to sharpen the contrast between land cover types: the Normalised Difference Vegetation Index for vegetation greenness, the Normalised Difference Water Index for surface water, and the Normalised Difference Built-up Index for urban surfaces.

The heart of the method was a Random Forest classifier, a machine learning algorithm that builds hundreds of decision trees from randomly sampled training data and assigns each pixel a class by majority vote. Nine predictor variables were used, combining six Landsat spectral bands with the three indices, and the classifier was configured with 100 decision trees. Reference points gathered from field surveys and high-resolution Google Earth imagery were split 70:30 into training and validation subsets. The resulting maps distinguished seven land use and land cover categories: dense forest, moderately dense forest, open forest, agriculture, built-up land, barren land and water bodies. Accuracy assessment using an independent confusion matrix yielded an overall accuracy of 81.57 percent and a Kappa coefficient of 0.78, figures the authors describe as good, though slightly below the conventional threshold of 0.80 that would indicate near-excellent agreement.

The classified maps tell a story of two opposing processes running in parallel. In 1995, open forest dominated the sanctuary at 45.4 percent of the area, with moderately dense forest at 21.8 percent and dense forest at 10.5 percent. By 2025, dense forest had fallen to just 5.1 percent and open forest to 38.9 percent, while built-up land climbed from 9.8 to 13.6 percent. Yet moderately dense forest expanded substantially, rising by 35.5 percent or 6.11 square kilometres, a pattern the researchers attribute to secondary succession, the regrowth of woody vegetation on land where pressure has eased or where former agricultural plots have been abandoned. This regenerative pulse, however, cannot compensate for the losses elsewhere. Water bodies, which covered 0.33 percent of the sanctuary in 1995, had dwindled to a mere 0.08 percent by 2025, a hydrological decline the authors link to the broader disturbance regime squeezing the reserve.

Beyond simple area statistics, the study deployed landscape ecology metrics to capture how the sanctuary’s structure, not just its extent, has changed. Shannon’s Diversity Index, which measures the variety and evenness of land cover classes, fluctuated across the period, dipping to 1.36 in 2005 before rising again to 1.49 by 2025. Patch count remained constant at seven discrete patches, but edge length told a more troubling tale: after falling from 68,958 metres in 1995 to 58,518 metres in 2005, total edge length surged to 70,749 metres by 2025. Longer edges mean more of the forest interior is exposed to external pressures such as grazing, fuelwood extraction, encroachment and microclimatic stress, a phenomenon ecologists call the edge effect. The authors interpret the combination of stable patch count and rising edge length as evidence of a landscape that is structurally fragmented yet ecologically dynamic, alternating between degradation and partial recovery.

To determine whether these changes represented genuine long-term trends or mere fluctuation, the team applied two complementary statistical tools. The Theil-Sen slope estimator, which calculates the median of all pairwise slopes in a time series, provides a robust, outlier-resistant measure of the magnitude of change, while the Mann-Kendall test assesses the statistical significance of monotonic trends using Z-statistics and p-values. The pixel-level analysis was unambiguous: 2,748 pixels showed significant decreasing trends between 1995 and 2025, more than double the 1,267 pixels showing positive trends, with 739 pixels remaining stable. In other words, despite pockets of regeneration, the sanctuary’s overall trajectory is one of degradation, and the authors argue that rapid intervention is required to manage the losses.

The spatial pattern of change points to specific drivers. The decline in dense forest and water bodies aligns with encroachment for settlement and agricultural expansion along the sanctuary’s western boundary, where it adjoins Guwahati, while the concentration of new built-up land near transport corridors implicates infrastructure development as a principal engine of forest loss at the periphery. The magnitude of the losses also stands out when set against comparable research: regional assessments in Northeast India have typically reported broad forest declines of roughly 9 to 10 percent, whereas Amchang’s 51.7 percent dense-forest loss over three decades far exceeds those figures, underscoring the severity of unchecked urban expansion and weak buffer-zone enforcement. The authors frame their findings within the Sustainable Development Goals, linking sustainable urban planning to SDG 11, forest conservation and climate mitigation to SDG 13, and ecosystem restoration to SDG 15.

What makes the study methodologically distinctive is its integration of three analytical strands, Random Forest classification, landscape fragmentation metrics and non-parametric trend statistics, within a single framework applied to a peri-urban protected area over 30 years. Because the entire workflow relies on freely available Landsat imagery and open-access processing in Google Earth Engine, the authors argue it can be readily transferred to other protected areas in data-poor settings facing similar pressures at the urban edge. The study is not without limitations: the 30-metre resolution of Landsat constrains the detection of fine-scale fragmentation, dry-season imagery cannot capture seasonal forest dynamics, and the classification accuracy, while respectable, leaves residual uncertainty that propagates into the fragmentation and trend analyses. The authors recommend future work with higher-resolution satellite data and deep learning classifiers. For now, the message from the satellites is clear: without stronger buffer-zone compliance and better land use planning around Guwahati, one of Northeast India’s most biodiverse sanctuaries will continue to erode at its edges, one pixel at a time.

Subject of Research: Three-decade geospatial assessment of land use and land cover change in a peri-urban protected area of Assam, India

Article Title: Spatio temporal land use and land cover changes in a peri urban protected area of Kamrup Metropolitan District, Assam, India using geospatial techniques

Article References: Changkakoti, T., Saikia, P., Borthakur, P., & Roy, M. (2026). Spatio temporal land use and land cover changes in a peri urban protected area of Kamrup Metropolitan District, Assam, India using geospatial techniques. Discover Forests, 2(1), Article 75. https://doi.org/10.1007/s44415-026-00134-4

Image Credits: AI Generated

DOI: 10.1007/s44415-026-00134-4

Keywords: land use land cover change, remote sensing, Random Forest classification, forest fragmentation, peri-urban protected area, Amchang Wildlife Sanctuary, Guwahati, Landsat, landscape metrics, Mann-Kendall test, biodiversity hotspot, urbanization