Remote Sensing in Land Use and Management

As an essential basic function of grassland resource surveys, grassland-type recognition is of great importance in both theoretical research and practical applications. For a long time, grassland-type recognition has mainly relied on two methods: manual recognition and remote sensing recognition. Among them, manual recognition is time-consuming and laborious, and easily affected by the level of expertise of the investigator, whereas remote sensing recognition is limited by the spatial resolution of satellite images, and is not suitable for use in field surveys. In recent years, deep learning techniques have been widely used in the image recognition field, but the application of deep learning in the field of grassland-type recognition needs to be further explored. Based on a large number of field and web-crawled grassland images, grassland-type recognition models are constructed using the PyTorch deep learning framework. During model construction, a large amount of knowledge learned by the VGG-19 model on the ImageNet dataset is transferred to the task of grassland-type recognition by the transfer learning method. By comparing the performances of models with different initial learning rates and whether or not data augmentation is used, an optimal grassland-type recognition model is established. Based on the optimal model, grassland resource-type map, and meteorological data, PyQt5 is used to design and develop a grassland-type recognition system that uses user-uploaded grassland images and the images’ location information to comprehensively recognize grassland types. The results of this study showed that: (1) When the initial learning rate was set to 0.01, the model recognition accuracy was better than that of the models using initial learning rates of 0.1, 0.05, 0.005, and 0.001. Setting a reasonable initial learning rate helps the model quickly reach optimal performance and can effectively avoid variations in the model. (2) Data augmentation increases the diversity of data, reducing the overfitting of the model; recognition accuracies of the models constructed using the augmented data can be improved by 3.07–4.88%. (3) When the initial learning rate was 0.01, modeling with augmented data and with a training epoch = 30, the model performance reached its peak—the TOP1 accuracy of the model was 78.32% and the TOP5 accuracy of the model was 91.27%. (4) Among the 18 grassland types, the recognition accuracy of each grassland type reached over 70.00%, and the probability of misclassification among most of the grassland types was less than 5.00%. (5) The grassland-type recognition system incorporates two reference grassland types to further improve the accuracy of grassland-type recognition; the accuracy of the two reference grassland types was 72.82% and 75.01%, respectively. The recognition system has the advantages of convenient information acquisition, good visualization, easy operation, and high stability, which provides a new approach for the intelligent recognition of grassland types using grassland images taken in a field survey. Full article

Timely and effective access to agricultural land-change information is of great significance for the government when formulating agricultural policies. Due to the vast area of Shandong Province, the current research on agricultural land use in Shandong Province is very limited. The classification accuracy of the current classification methods also needs to be improved. In this paper, with the support of the Google Earth Engine (GEE) platform and based on Landsat 8 time series image data, a multiple machine learning algorithm was used to obtain the spatial variation distribution information of agricultural land in Shandong Province from 2016 to 2020. Firstly, a high-quality cloud-free synthetic Landsat 8 image dataset for Shandong Province from 2016 to 2020 was obtained using GEE. Secondly, the thematic index series was calculated to obtain the phenological characteristics of agricultural land, and the time periods with significant differences in terms of water, agricultural land, artificial surface, woodland and bare land were selected for classification. Feature information, such as texture features, spectral features and terrain features, was constructed, and the random forest method was used to select and optimize the features. Thirdly, the random forest, gradient boosting tree, decision tree and ensemble learning algorithms were used for classification, and the accuracy of the four classifiers was compared. The information on agricultural land changes was extracted and the causes were analyzed. The results show the following: (1) the multi-spatial index time series method is more accurate than the single thematic index time series when obtaining phenological characteristics; (2) the ensemble learning method is more accurate than the single classifier. The overall classification accuracy of the five agricultural land-extraction results in Shandong Province obtained by the ensemble learning method was above 0.9; (3) the annual decrease in agricultural land in Shandong Province from 2016 to 2020 was related to the increase in artificial land-surface area and urbanization rate. Full article

Using a shape model (SM) is a typical method to determine the phenological phases of crops with long-time-series satellite remote sensing data. The average AGDD-based shape model (AAGDD-SM) takes temperature into account compared to SM, however, the commonly used daily average temperature is not sufficient to determine the exact AGDD owing to the possibly significant changes in temperatures throughout the day. In this paper, a modified shape model was proposed for the better estimation of phenological dates and it is incorporated into the continuous AGDD (CAGDD) which was calculated based on temperatures from a continuous 24 h within a day, different from the calendar day or the average AGDD indicators. In this study, the CAGDD replaced the abscissa of the NDVI growth curve over a 5-year period (2014 to 2018, excluding 2015) for a test site of early rice in Jiangxi province of China. Four key phenological phases, including the reviving, tillering, heading and anthesis phases, were selected and determined with reference to the field-observed phenological data. The results show that compared with the AAGDD-SM, the method proposed in this paper has basically improved the prediction of each phenological period. For those cases where the average temperature is lower than the minimum temperatures (K1) but the effective accumulated temperature is not zero, more accurate AGDD can be calculated according to the method in this paper. Full article

In recent years, the resolution of remote sensing images, especially aerial images, has become higher and higher, and the spans of time and space have become larger and larger. The phenomenon in which one class of objects can produce several kinds of spectra may lead to more errors in detection methods that are based on spectra. For different convolution methods, downsampling can provide some advanced information, which will lead to rough detail extraction; too deep of a network will greatly increase the complexity and calculation time of a model. To solve these problems, a multifunctional feature extraction model called MSNet (multifunctional feature-sharing network) is proposed, which is improved on two levels: depth feature extraction and feature fusion. Firstly, a residual shuffle reorganization branch is proposed; secondly, linear index upsampling with different levels is proposed; finally, the proposed edge feature attention module allows the recovery of detailed features. The combination of the edge feature attention module and linear index upsampling can not only provide benefits in learning detailed information, but can also ensure the accuracy of deep feature extraction. The experiments showed that MSNet achieved 81.33% MIoU on the Landover dataset. Full article

Many strategies have been put forward to seek green and low-carbon development, some of which are achieved through land use and cover change (LUCC). A series of land management policies related to LUCC and corresponding changes in carbon dynamics were released with the implementation of the Ecological Conservation Pilot Zone Program (ECPZP) in China. We explored the spatiotemporal dynamics of LUCC and carbon storage in the first ECPZP implementation region (Fujian province) at the time before and after ECPZP implementation using a simplified carbon pools model and quantified the relative impacts of human activities and climate change on net primary productivity (NPP) employing residual analysis. This can fill the gap of land use and vegetation changes and the corresponding carbon dynamics in the ECPZP region and can serve as a reference for future land management policy revisions and ECPZP project extensions. The results showed that: (1) In 1990–2020, woodland, cultivated land, and grassland were the leading land use type in Fujian province. The area of LUCC was 11,707.75 km², and it was predominantly caused by the conversion from cultivated land to built-up land, and the interconversion between woodland and grassland. (2) An increase of 9.74 Tg in carbon storage was mainly caused by vegetation conversion from 1990 to 2020. (3) The statistically significant increased area of climate change-induced NPP was 2.3% primarily in the northwest, but the decreased area of it statistically significantly was only 0.1%. Correspondingly, the increased area of statistically significant human activity-induced NPP was 8.7% primarily in the southeast, but the decreased area of statistically significance was 6.5%, mostly in the central region. In addition, the statistically significant areas of NPP caused by the combination of human activities and climate change differed by 1.8%. To sum up, ECPZP makes full use of the vertical mountain landscape and property right reform to effectively secure ecological space and local income. Moreover, urbanization-related policies are an essential impetus for LUCC and carbon balance. The impact of other built-up land expansion on environmental change needs to be paid particular attention to. Moreover, land-use activities in the centre of the study region that are not conducive to NPP growth should be judiciously assessed in the future. Full article

Ecological degradation has occurred in global grasslands and has impaired their ecosystem services severely, so ecological conservation of grasslands should be focused more on the effectiveness of management measures. The green-up process decides the year-round forage yield and ecological conditions of grasslands. Adopting rest-grazing during the green-up process can guarantee a successful green-up, thus realizing more economic benefits without grassland degradation. Therefore, studies should pay more attention to whether the green-up process is really covered by the rest-grazing period or not. We analyze the spatiotemporal variations and the stability of the annual green-up date in Xilin Gol Grassland from 2000 to 2018 based on MODIS time series images and compare the green-up date with the rest-grazing period to assess the effectiveness of the rest-grazing policy. The results show that the green-up date of Xilin Gol Grassland had advanced 15 days on average because of the increasing trend of both temperature and precipitation during 2000~2018. The green-up date is mostly 120~130 d in the east, about 10 days earlier than the west (130~140 d) and 20 days earlier than in the central areas (140~150 d), also because of the spatial variations of temperature and precipitation. The coefficient of variation (CV) of the green-up date showed a significant negative correlation with precipitation, so the green-up date is more unstable in the arid areas. The rest-grazing period started more than 45 days earlier than the green-up date and failed to cover it in several years, which occurred more frequently in southern counties. The average green-up date appeared after rest-grazing started in over 98% of areas, and the time gap is 15~45 days in 88% of areas, which not only could not avoid grassland degradation effectively but also increased herdsmen’s life burden. This study aims to accurately grasp the temporal and spatial variations of the green-up date in order to provide references for adjusting a more proper rest-grazing period, thus promoting ecological conservation and sustainable development of animal husbandry. Full article

Cultivated land resources are crucial to food security and economic development. Exploring the spatiotemporal pattern of cultivated land non-agriculturalization and its drivers is a prerequisite for cultivated land conservation. This paper used GlobeLand30 data to reveal the spatial and temporal pattern, the shift of the gravity center and the drivers of cultivated land non-agriculturalization by employing spatial analysis, gravity center model and the geographical detector model. The results show a dramatic increase in the non-agriculturalization of cultivated land in the period of 2010–2020 compared to 2000–2010. Spatially, the cultivated land non-agriculturalization mainly occurred in areas with high urbanization levels, such as eastern Sichuan Province and western Chongqing Municipality, while the cultivated land non-agriculturalization in other areas was small-scale and spatially scattered. Furthermore, the speed of cultivated land non-agriculturalization showed spatial unevenness, and the gravity center of cultivated land non-agriculturalization shifted towards the northeast at a distance of 123.21 km. The cultivated land non-agriculturalization was affected by GDP per capita, population density, GDP per unit of land and total retail sales of social consumer goods. The key drivers for the cultivated land non-agriculturalization in the study area were the continuous expansion of urban space and the large-scale cultivation of economic fruit trees. The government should promote small-scale machinery suitable for agricultural cultivation in the mountainous and hilly areas of Southwest China, and appropriately develop economic fruit groves and livestock farming to reduce the phenomenon of cultivated land non-foodization. Full article

Land-use change is supposed to exert significant effects on the spatio-temporal patterns of ecosystem carbon storage in arid regions, while the relative size of land-use change effect under future environmental change conditions is still less quantified. In this study, we combined a land-use change dataset with a satellite-based high-resolution biomass and soil organic carbon dataset to determine the role of land-use change in affecting ecosystem carbon storage from 1980 to 2050 in the Gansu province of China, using the MCE-CA-Markov and InVEST models. In addition, to quantify the relative size of the land-use change effect in comparison with other environmental drivers, we also considered the effects of climate change, CO₂ enrichment, and cropland and forest managements in the models. The results show that the ecosystem carbon storage in the Gansu province increased by 208.9 ± 99.85 Tg C from 1980 to 2020, 12.87% of which was caused by land-use change, and the rest was caused by climate change, CO₂ enrichment, and ecosystem managements. The land-use change-induced carbon sequestration was mainly associated with the land-use category conversion from farmland to grassland as well as from saline land and desert to farmland, driven by the grain-for-green projects in the Loess Plateau and oasis cultivation in the Hexi Corridor. Furthermore, it was projected that ecosystem carbon storage in the Gansu province from 2020 to 2050 will change from −14.69 ± 12.28 Tg C to 57.83 ± 53.42 Tg C (from 105.62 ± 51.83 Tg C to 177.03 ± 94.1 Tg C) for the natural development (ecological protection) scenario. By contrast, the land-use change was supposed to individually increase the carbon storage by 56.46 ± 9.82 (165.84 ± 40.06 Tg C) under the natural development (ecological protection) scenario, respectively. Our results highlight the importance of ecological protection and restoration in enhancing ecosystem carbon storage for arid regions, especially under future climate change conditions. Full article

The transformation of resource-exhausted urban land is an urgent problem for sustainable urban development in the world today. Obtaining the urban land use type and analyzing the changes in their land use can lead to better management of the relationship between economic development and resource utilization. In this paper, a residual-intelligent module network was proposed to solve the problems of low classification accuracy and missing objects edge information in traditional computer classification methods. The classification of four Landsat-TM/OLI images from 1993–2020 for Jiaozuo city (the first batch of resource-exhausted cities in China) was realized by this method. The results (overall accuracy was 98.61%, in 2020 images) were better than the comparison models (support vector machine, 2D-convolutional neural network, hybrid convolution networks; overall accuracy was 87.12%, 96.16%, 98.46%, respectively) and effectively reduced the loss of information on the edge of the ground objects. On this basis, six main land use types were constructed by combining field surveys and other methods. The characteristics and driving forces of spatial-temporal change in land use were explored from the aspect of social, economic and policy factors. The results showed that from 1993 to 2020 the cultivated land, forest land, water body and other land types in the study area decreased by 690.97 km², 57.54 km², 47.04 km² and 59.43 km², respectively. The construction land and bare land increased by 839.38 km² and 15.57 km², respectively. The transfer of land use types was mainly from cultivated land to construction land, with a cumulative conversion of 920.95 km² within 27 years. The driving forces of land use in the study area were analyzed by principal component analysis (PCA) and regression analysis. The spatial-temporal evolution of land use types was affected by policy changes, the level of social development and the adjustment in the economy, industry and agriculture structure. The investment in fixed assets and per capita net income in rural areas were the top two influencing factors and their cumulative contribution rate was 94.62%. The findings of this study can provide scientific reference and theoretical support for land use planning, land reclamation in mining areas, ecological protection and sustainable development in Jiaozuo and other resource-exhausted cities in the world. Full article

Updated and accurate land cover maps are essential and crucial for sustainable crop production and efficient land management. However, accurate and efficient land cover mapping is still a challenge for agricultural regions with complicated landscapes. This study proposed a novel spectral-phenological based land cover classification (SPLC) method to identify the land cover for fragmented agricultural landscapes, with less requirement of ground truth data. The SPLC method integrated a pixel-based support vector machine (SVM) algorithm for cropland and various non-cropland classification, and a phenology-based automatic decision tree algorithm for identification of various crop types. It was then tested and applied in two typical case areas (i.e., Jiyuan in the upstream and Yonglian in the downstream) of Hetao Irrigation District (Hetao) in the upper Yellow River basin (YRB), northwest China. The field survey sampling data and the regional visual interpretation maps were jointly used to evaluate the accuracy of land cover classification. Results indicated that stable phenological rules can be established for crop identification even with complex planting patterns, and the SPLC method performed well in land cover mapping in case areas. Four high-accuracy land cover maps were produced for Jiyuan in 2020 and 2021, Yonglian in 2021, and Hetao in 2021. The overall accuracies (OA) can reach 0.90–0.94 based on evaluation with abundant ground truth data, and land cover maps agreed well with the visual interpretation maps in space. Overall, the case application validated the applicability and efficiency of the SPLC method in land cover mapping for regions with fragmented agricultural landscapes, and also implied the potential use in other similar regions. Full article

Accurately mapping surface water fractions is essential to understanding the distribution and area of small water bodies (SWBs), which are numerous and widespread. Traditional spectral unmixings based on the linear mixture model require high-quality prior endmember information, and are not appropriate in situations such as dealing with multiple scattering effects. To overcome difficulties with unknown mixing mechanisms and parameters, a novel automated and hierarchical surface water fraction mapping (AHSWFM) for mapping SWBs from Sentinel-2 images was proposed. AHSWFM is automated, requires no endmember prior knowledge and uses self-trained regression using scalable algorithms and random forest to construct relationships between the multispectral data and water fractions. AHSWFM uses a hierarchical structure that divides pixels into pure water, pure land and mixed water-land pixels, and predicts their water fractions separately to avoid overestimating water fractions for pure land pixels and underestimating water fractions for pure water pixels. Results show that using the hierarchical strategy can increase the accuracy in estimating SWB areas. AHSWFM predicted SWB areas with a root mean square error of approximately 0.045 ha in a region using more than 1200 SWB samples that were mostly smaller than 0.75 ha. Full article