Abstract：
Monitoring the dynamics of land use and land cover (LULC) is imperative in the changing climate and evolving urbanization patterns worldwide. The shifts in land use have a significant impact on the hydrological response of watersheds across the globe. Several studies have applied machine learning (ML) algorithms using historical LULC maps along with elevation data and slope for predicting future LULC projections. However, the influence of other driving factors such as socio-economic and climatological factors has not been thoroughly explored. In the present study, a sensitivity analysis approach was adopted to understand the effect of both physical (elevation, slope, aspect, etc.) and socio-economic factors such as population density, distance to built-up, and distance to road and rail, as well as climatic factors (mean precipitation) on the accuracy of LULC prediction in the Brahmani and Baitarni (BB) basin of Eastern India. Additionally, in the absence of the recent LULC maps of the basin, three ML algorithms, i.e., random forest (RF), classified and regression trees (CART), and support vector machine (SVM) were utilized for LULC classification for the years 2007, 2014, and 2021 on Google earth engine (GEE) cloud computing platform. Among the three algorithms, RF performed best for classifying built-up areas along with all the other classes as compared to CART and SVM. The prediction results revealed that the proximity to built-up and population growth dominates in modeling LULC over physical factors such as elevation and slope. The analysis of historical data revealed an increase of 351% in built-up areas over the past years (2007-2021), with a corresponding decline in forest and water areas by 12% and 36% respectively. While the future predictions highlighted an increase in built-up class ranging from 11 to 38% during the years 2028-2070, the forested areas are anticipated to decline by 4 to 16%. The overall findings of the present study suggested that the BB basin, despite being primarily agricultural with a significant forest cover, is undergoing rapid expansion of built-up areas through the encroachment of agricultural and forested lands, which could have far-reaching implications for the region\'s ecosystem services and sustainability.
摘要：
在全球气候变化和不断发展的城市化模式中，必须监测土地利用和土地覆盖（LULC）的动态。土地利用的变化对全球流域的水文响应具有重大影响。一些研究已经应用了机器学习（ML）算法，使用历史LULC地图以及高程数据和坡度来预测未来的LULC预测。然而,尚未彻底探索其他驱动因素的影响，例如社会经济和气候因素。在本研究中,采用敏感性分析方法来了解两种物理(海拔，斜坡,方面,等。)和人口密度等社会经济因素，距离建筑，以及到公路和铁路的距离，以及气候因素（平均降水量）对印度东部Brahmani和Baitarni（BB）盆地LULC预测准确性的影响。此外,在没有最近的盆地LULC地图的情况下，三种ML算法，即，随机森林(RF)，分类和回归树(CART)，和支持向量机（SVM）在2007年，2014年和2021年在GoogleEarth引擎（GEE）云计算平台上用于LULC分类。在这三种算法中，与CART和SVM相比，RF在对建筑区域以及所有其他类别进行分类方面表现最佳。预测结果表明，在对诸如海拔和坡度之类的物理因素进行LULC建模时，靠近建筑物和人口增长占主导地位。对历史数据的分析显示，过去几年(2007-2021年)建成区增长了351%，森林和水域面积分别相应减少12%和36%。虽然未来的预测强调了2028-2070年期间建筑等级的增长从11％到38％不等，但森林面积预计将下降4％至16％。本研究的总体结果表明，BB盆地，尽管主要是农业，森林覆盖率很高，正在通过侵占农业和林地迅速扩大建成区，这可能对该地区的生态系统服务和可持续性产生深远的影响。
