Evapotranspiration plays a crucial role in the surface hydrothermal balance. On a regional scale, especially in the blown-sand areas, an accurate estimate of evapotranspiration has important guiding significance for a rational allocation of water resources and drought monitoring. The objective of the study is to estimate the surface evapotranspiration for the blown-sand region in the Ordos Basin based on the Surface Energy Balance Algorithm for Land (SEBAL) model using six phases of Landsat 8 remote sensing images during 2015–2016 and the corresponding surface meteorological observational data, analyze the characteristics of temporal and spatial distributions of evapotranspiration in the study area. The results show that (1) the daily evapotranspiration presents a seasonal variability with the highest in summer, lower in autumn and spring, and the lowest in winter; (2) the evapotranspiration is distinctly characterized by its spatial variability, which is related to the terrain and geomorphology in this area as well as the effect of human activities; and (3) the daily evapotranspiration estimated by the SEBAL model was validated using the Food and Agriculture Organization (FAO) Penman-Monteith (P–M) model, which yielded an mean relative error (MRE) of 19.5%. In summary, the remote sensing data based SEBAL model can be applied to robustly estimate evapotranspiration for the blown-sand regions, and the study results can be served as an important reference for the research of water circulation, rational utilization of water resources, and protection of the ecological environment in the arid and semi-arid regions.
Personalized travel itinerary recommendation algorithms are the focus of research in smart tourism and tourism GIS. Aiming to address issues present in travel itinerary recommendations for the increasingly popular “self-drive tour” mode, this study proposes an algorithm based on comprehensive tourist satisfaction to mitigate problems such as the neglect of important relevant factors and low degree of personalization. First, we construct a model of tourist satisfaction for travel itineraries by comprehensively considering factors including time utilization, the attractiveness of attractions, itinerary feasibility, and the diversity of attraction types. Unlike previous studies, we consider dining and accommodation time during the itinerary, the physical condition of tourists, and the diversity of attraction types, and establish penalty functions to flexibly constrain deviations from the expected conditions in itinerary planning. Then, with the optimization of comprehensive tourist satisfaction as the objective, we design a new algorithm to address the itinerary recommendation problem, supporting tourists in selecting must-visit attractions, restaurants, and hotels, as well as personalized preferences such as the sightseeing sequence. The experimental results demonstrate that our proposed algorithm outperforms two baseline algorithms, providing higher comprehensive tourist satisfaction while also exhibiting greater feasibility in itinerary planning. The proposed algorithm effectively addresses the issue of personalized travel itinerary recommendation, presenting an efficient, feasible, and practical solution.
Background: With the growth of trajectory data, the large amount of data causes a lot of problems with storage, analysis, mining, etc. Most of the traditional trajectory data compression methods are focused on preserving spatial characteristic information and pay little attention to other temporal information on trajectory data, such as speed change points or stop points. Methods: A data compression algorithm based on the spatio-temporal characteristics (CASC) of the trajectory data is proposed to solve this problem. This algorithm compresses trajectory data by taking the azimuth difference, velocity difference and time interval as parameters in order to preserve spatial-temporal characteristics. Microsoft’s Geolife1.3 data set was used for a compression test to verify the validity of the algorithm. The compression results were compared with the traditional Douglas-Peucker (DP), Top-Down Time Ratio (TD-TR) and Opening Window (OPW) algorithms. Compression rate, the direction information of trajectory points, vertical synchronization distance, and algorithm type (online/offline) were used to evaluate the above algorithms. Results: The experimental results show that with the same compression rate, the ability of the CASC to retain the forward direction trajectory is optimal, followed by TD-TR, DP, and then OPW. The velocity characteristics of the trajectories are also stably retained when the speed threshold value is not more than 100%. Unlike the DP and TD-TR algorithms, CASC is an online algorithm. Compared with OPW, which is also an online algorithm, CASC has better compression quality. The error distributions of the four algorithms have been compared, and CASC is the most stable algorithm. Taken together, CASC outperforms DP, TD-TR and OPW in trajectory compression.
Surface evapotranspiration (ET) is an important part of the hydrological cycle. Based on the MOD16 ET product and the data collected by meteorological stations, this study investigated, for the first time, the characteristics, variation trend and influencing factors of actual ET in Ningxia from 2001 to 2020 along temporal and spatial scales using the Theil–Sen median trend analysis, Mann–Kendall test and Hurst index, and predicted the future trend of ET. The results revealed a strong correlation between the MOD16 ET product and ET data collected at meteorological stations (r = 0.837, R2 = 0.701). Over the past 20 years, the annual ET in Ningxia showed an overall increasing trend, and the proportion of the increasing area was 96.58%. Quarterly ET varied over time, with the highest value in the third quarter and the lowest value in the second quarter. Annual ET showed a positive correlation with normalized difference vegetation index (NDVI), surface temperature and precipitation but no correlation with relative humidity. Additionally, the Hurst index revealed areas showing a persistent increase in ET, accounting for 84.91% of the total area, indicating that the future trend of ET in Ningxia is consistent with the past trend.
26 April 2018 in International Journal of Remote Sensing
Suspended sediment concentration (SSC) is one of the most important parameters for marine water quality and environmental evaluations. Using remote-sensing technology, the macroscopic, real-time, and continuous monitoring of SSC can be achieved. The study based on in-situ sediment concentration data and spectral data from the Gulf of Bohai, China, developed a statistical regression model, a principal component analysis model, a neural network model, and a semi-analytical model for the sediment concentration retrieval and assessed the accuracy and applicability of the four kinds of models. The results indicate that the inversion precision of the statistical regression model and semi-analytical model are relatively better than other models. And compared with statistical regression model, semi-analytical model has higher inversion precision and better applicability over the whole study area. Principal component analysis model is insensitive to lower SSC levels and suitable for the regions with an average SSC level higher than 50 mg l−1. Neural network model has not achieved an ideal inversion precision in the whole areas and at all SSC levels. According to the results, a semi-analytical model was proposed to retrieve the SSC in the study area. The retrieved SSCs were mainly concentrated in a range of 25–75 mg l−1 and the SSC levels had a spatial characteristic which was higher in the southern waters than that in the northern areas and in the coastal waters was higher than that in the deep sea. These results can provide support for further study of the migration of marine sediment and serve as a reference for SSC inversion model selection in the similar regions.
12 May 2023 in International Journal of Remote Sensing
Water eutrophication has become one of the prominent problems of environmental protection in inland watersheds. Turbidity, total phosphorus (TP) and total nitrogen (TN) concentrations are key water quality parameters (WQPs) that reflect the level of water eutrophication in inland waters. Due to the complex interaction effects between different water quality in urban rivers, the water quality retrieval models still have the problem of single input features and poor applicability. This paper proposed a robust feature selection method based on machine learning and utilized Sentinel-2 remote sensing images for water quality retrieval of Chan and Ba rivers in Xi’an City. The ReliefF and global sensitivity analysis (GSA) methods (ReliefF-GSA) were used to select the optimal feature combination from the potential feature dataset. Based on the optimal feature combination, Random Forest regression (RFR), LightGBM and XGboost models were constructed for the three WQPs retrieval, respectively. The optimal models were then used to invert the three WQPs and the spatial-temporal variation of WQPs from January 2021 to January 2022 was analysed. The results show that (1) The RelieF-GSA method is suitable for high-dimensional feature filtration and enables optimal feature selection for specific WQPs retrieval. It is revealed that the BOI index (black odour water index) is the key feature for the retrieval of turbidity and TN concentration. (2) The RFR model was found to be better than other models and more appropriate for Chan and Ba rivers, with coefficients of determination (R2) of 0.90, 0.89 and 0.81, respectively. (3) It was found that the water qualities in the Chan and Ba rivers have prominent seasonal characteristics. Turbidity and TP concentrations showed higher, while TN concentration showed relatively low in autumn. The method and conclusions of this paper can further provide a reference for WPQs retrieval in urban rivers.