Abstract:With the rapid advances in sensors of remote sensing satellites, a large number of high-resolution images (HRIs) can be accessed every day. Land use classification using high-resolution images has become increasingly important as it can help to overcome the problems of haphazard, deteriorating environmental quality, loss of prime agricultural lands, and destruction of important wetlands, and so on. Recently, local feature with bag-of-words (BOW) representation has been successfully applied to land-use scene classification with HRIs. However, the BOW representation ignores information from scene labels, which is critical for scene-level land-use classification. Several algorithms have incorporated information from scene labels into BOW by calculating a class-specific codebook from the universal codebook and coding a testing image with a number of histograms. Those methods for mapping the BOW feature to some inaccurate class-specific codebooks may increase the classification error. To effectively solve this problem, we propose an improved class-specific codebook using kernel collaborative representation based classification (KCRC) combined with SPM approach and SVM classifier to classify the testing image in two steps. This model is robust for categories with similar backgrounds. On the standard Land use and Land Cover image dataset, the improved class-specific codebook achieves an average classification accuracy of 93% and demonstrates superiority over other state-of-the-art scene-level classification methods.

China has a great wealth of lake resources over a great spatial extent and these lakes are highly sensitive to climate changes through their heat and water budgets. However, little is known about the changes in lake surface water temperature (LSWT) across China under the climate warming conditions over the past few decades. In this study, MODIS land surface temperature (LST) data were used to examine the spatial and temporal (diurnal, intra-annual, and inter-annual) variations in LSWT of China’s lakes during 2001–2016. Our results indicated that 169 large lakes included in the study exhibited an overall increasing trend in LSWT, with an average rate of 0.26 °C/decade. The increasing rate of nighttime LSWT is 0.31 °C/decade, faster than that of daytime temperature (0.21 °C/decade). Overall, 121 (71.6%) lakes showed an increase in daytime temperature with a mean rate of 0.38 °C/decade, while the rest 48 (28.4%) lakes decreased in temperature with a mean rate of − 0.21 °C/decade. We also quantitatively analyzed the relationship of the lake surface temperature and diurnal temperature differences (DTDs) with geographical location, topography, and lake morphometry by utilizing multivariate regression analysis. Our analysis suggested that the geographical location (latitude and longitude) and topography (altitude) were primary driving factors in explaining the national lake water temperature variation (P < 0.001), which were also mediated by morphometric factors such as lake surface area and volume. Moreover, the diurnal lake temperature variations were significantly correlated with altitude, latitude, and lake surface area (R2 = 0.426, P < 0.001). Correlation analyses of LSWT trend and air temperature trend for each lake indicated that LSWT was positively correlated with air temperature in both daytime and nighttime for most lakes.

No abstract

No abstract

No abstract