Lake surface water temperature (LSWT) is an important factor of water ecological environment. In the context of global warming, the LSWT of global lakes generally reveals an upward trend. With a continuous intensification of human activities and a rapid expansion of the impervious surface, urbanization has exerted an increasing impact on the environment, so the impact of human activities on LSWT cannot be ignored. Because of the special geographical location, the change of LSWT in plateau lakes has important impacts on climate diversity, biodiversity, and cultural diversity. As a result, it is critical to monitor and model the variation characteristics of LSWT in the plateau area. Based on the data set of natural factors representing climate change and human factors representing human activities, this study proposes a classification of lake types by K‐Means clustering method. At watershed scale, 11 lakes in the study area are divided into three types: Natural Lake, Semi‐urban Lake, and Urban Lake (UL). Based on this classification, the variation characteristics of LSWT for the eleven lakes from 2001 to 2017 are analyzed. The causal relationship and contribution of climate change and human activities to the rise of LSWT are discussed. Results show that (1) from 2001 to 2017, the annual mean of LSWT‐day/night and near‐surface air temperature in the 11 lakes show a warming trend, a significant correlation (R = 0.82, α = 0.0164 < 0.5) and a same periodicity, which indicates that near‐surface air temperature is one of the main influencing factors of LSWT warming in Yunnan‐Guizhou Plateau. (2) LSWT warming trend of UL is more obvious than those of Semi‐urban Lake and Natural Lake, indicating that human activities have more significant impact on LSWT of UL. The main driving factors are the impervious surface expansion and population increase. (3) The influence of human activities on the LSWT in Yunnan‐Guizhou Plateau is becoming more and more significant, and it is also the main factor in causing the deterioration of lake water environment in Yunnan‐Guizhou Plateau.

Terraces are the major land-use type of agriculture and support the main agricultural production in southeast and southwest China. However, due to smallholder farming, complex terrains, natural disasters and illegal land occupations, a light-weight and low cost dynamic monitoring of agricultural terraces has become a serious concern for smallholder production systems in the above area. In this work, we propose a small unmanned aerial vehicle (UAV) based multi-temporal image registration method that plays an important role in transforming multi-temporal images into one coordinate system and determines the effectiveness of the subsequent change detection for dynamic agricultural terrace monitoring. The proposed method consists of four steps: (i) guided image filtering based agricultural terrace image preprocessing, (ii) texture and geometric structure features extraction and combination, (iii) multi-feature guided point set registration, and (iv) feature points based image registration. We evaluated the performance of the proposed method by 20 pairs of aerial images captured from Longji and Yunhe terraces, China using a small UAV (the DJI Phantom 4 Pro), and also compared against four state-of-the-art methods where our method shows the best alignments in most cases.