Search

High-quality training samples are essential for accurate land cover classification. Due to the difficulties in collecting a large number of training samples, it is of great significance to collect a high-quality sample dataset with a limited sample size but effective sample distribution. In this paper, we proposed an object-oriented sampling approach by segmenting image blocks expanded from systematically distributed seeds (object-oriented sampling approach) and carried out a rigorous comparison of seven sampling strategies, including random sampling, systematic sampling, stratified sampling (stratified sampling with the strata of land cover classes based on classification product, Latin hypercube sampling, and spatial Latin hypercube sampling), object-oriented sampling, and manual sampling, to explore the impact of training sample distribution on the accuracy of land cover classification when the samples are limited. Five study areas from different climate zones were selected along the China–Mongolia border. Our research identified the proposed object-oriented sampling approach as the first-choice sampling strategy in collecting training samples. This approach improved the diversity and completeness of the training sample set. Stratified sampling with strata defined by the combination of different attributes and stratified sampling with the strata of land cover classes had their limitations, and they performed well in specific situations when we have enough prior knowledge or high-accuracy product. Manual sampling was greatly influenced by the experience of interpreters. All these sampling strategies mentioned above outperformed random sampling and systematic sampling in this study. The results indicate that the sampling strategies of training datasets do have great impacts on the land cover classification accuracies when the sample size is limited. This paper will provide guidance for efficient training sample collection to increase classification accuracies.

Urban land use mapping is critical to understanding human activities in space. The first national mapping result of essential urban land use categories of China (EULUC-China) was released in 2019. However, the overall accuracies in some of the plain cities such as Beijing, Chengdu, and Zhengzhou were lower than 50% because many parcel-based mapping units are large with mixed land uses. To address this shortcoming, we proposed an area of interest (AOI)-based mapping approach, choosing Beijing as our study area. The mapping process includes two major steps. First, grids with different sizes (i.e., 300 m, 200 m, and 100 m) were derived from original land parcels to obtain classification units with a suitable size. Then, features within these grids were extracted from Sentinel-2 spectral data, point of interest (POI), and Tencent Easygo crowdedness data. These features were classified using a random forest (RF) classifier with AOI data, resulting in a 10-category map of EULUC. Second, we superimposed the AOIs layer on classified units to do some rectification and offer more details at the building scale. The overall accuracy of the AOI layer reached 98%, and the overall accuracy of the mapping results reached 77%. This study provides a fast method for accurate geographic sample collection, which substantially reduces the amount of fieldwork for sample collection and improves the classification accuracy compared to previous EULUC mapping. The detailed urban land use map could offer more support for urban planning and environmental policymaking.

Land cover (LC) information plays an important role in different geoscience applications such as land resources and ecological environment monitoring. Enhancing the automation degree of LC classification and updating at a fine scale by remote sensing has become a key problem, as the capability of remote sensing data acquisition is constantly being improved in terms of spatial and temporal resolution. However, the present methods of generating LC information are relatively inefficient, in terms of manually selecting training samples among multitemporal observations, which is becoming the bottleneck of application-oriented LC mapping. Thus, the objectives of this study are to speed up the efficiency of LC information acquisition and update. This study proposes a rapid LC map updating approach at a geo-object scale for high-spatial-resolution (HSR) remote sensing. The challenge is to develop methodologies for quickly sampling. Hence, the core step of our proposed methodology is an automatic method of collecting samples from historical LC maps through combining change detection and label transfer. A data set with Chinese Gaofen-2 (GF-2) HSR satellite images is utilized to evaluate the effectiveness of our method for multitemporal updating of LC maps. Prior labels in a historical LC map are certified to be effective in a LC updating task, which contributes to improve the effectiveness of the LC map update by automatically generating a number of training samples for supervised classification. The experimental outcomes demonstrate that the proposed method enhances the automation degree of LC map updating and allows for geo-object-based up-to-date LC mapping with high accuracy. The results indicate that the proposed method boosts the ability of automatic update of LC map, and greatly reduces the complexity of visual sample acquisition. Furthermore, the accuracy of LC type and the fineness of polygon boundaries in the updated LC maps effectively reflect the characteristics of geo-object changes on the ground surface, which makes the proposed method suitable for many applications requiring refined LC maps.

Land-cover map is the basis of research and application related to urban planning, environmental management and ecological protection. Land-cover updating is an essential task especially in a rapidly urbanizing region, where fast development makes it necessary to monitor land-cover change in a timely manner. However, conventional approaches always have the limitations of large amounts of sample collection and exploitation of relational knowledge between multi-modality remote sensing datasets. With some global land-cover products being available, it is important to produce new land-cover maps based on the existing land-cover products and time series images. To this end, a novel transfer learning based automatic approach was proposed for updating land cover maps of rapidly urbanizing regions. In detail, the proposed method is composed of the following three steps. The first is to design a strategy to extract reliable land-cover information from the historical land-cover map for one of the images (source domain). Then, a novel relational knowledge transfer technique is applied to transfer label information. Finally, classifiers are trained on the transferred samples with spatio-spectral features. The experimental results show that aforementioned steps can select sufficient effective samples for target images, and for the main land-cover classes in a rapidly urbanizing region; the results of an updated map show good performance in both precision and vision. Therefore, the proposed approach provides an automatic solution for urban land-cover mapping with a high degree of accuracy.

Precise vegetation maps of mountainous areas are of great significance to grasp the situation of an ecological environment and forest resources. In this paper, while multi-source geospatial data can generally be quickly obtained at present, to realize effective vegetation mapping in mountainous areas when samples are difficult to collect due to their perilous terrain and inaccessible deep forest, we propose a novel and intelligent method of sample collection for machine-learning (ML)-based vegetation mapping. First, we employ geo-objects (i.e., polygons) from topographic partitioning and constrained segmentation as basic mapping units and formalize the problem as a supervised classification process using ML algorithms. Second, a previously available vegetation map with rough-scale label information is overlaid on the geo-object-level polygons, and candidate geo-object-based samples can be identified when all the grids’ labels of vegetation types within the geo-objects are the same. Third, various kinds of geo-object-level features are extracted according to high-spatial-resolution remote sensing (HSR-RS) images and multi-source geospatial data. Some unreliable geo-object-based samples are rejected in the candidate set by comparing their features and the rules based on local expert knowledge. Finally, based on these automatically collected samples, we train the model using a random forest (RF)-based algorithm and classify all the geo-objects with labels of vegetation types. A case experiment of Taibai Mountain in China shows that the methodology has the ability to achieve good vegetation mapping results with the rapid and convenient sample collection scheme. The map with a finer geographic distribution pattern of vegetation could clearly promote the vegetation resources investigation and monitoring of the study area; thus, the methodological framework is worth popularizing in the mapping areas such as mountainous regions where the field survey sampling is difficult to implement.

Spartina alterniflora (S. alterniflora) is one of the worst plant invaders in the coastal wetlands of China. Accurate and repeatable mapping of S. alterniflora invasion is essential to develop cost-effective management strategies for conserving native biodiversity. Traditional remote-sensing-based mapping methods require a lot of fieldwork for sample collection. Moreover, our ability to detect this invasive species is still limited because of poor spectral separability between S. alterniflora and its co-dominant native plants. Therefore, we proposed a novel scheme that uses an ensemble one-class classifier (EOCC) in combination with phenological Normalized Difference Vegetation Index (NDVI) time-series analysis (TSA) to detect S. alterniflora. We evaluated the performance of the EOCC algorithm in two scenarios, i.e., single-scene analysis (SSA) and NDVI-TSA in the core zones of Yancheng National Natural Reserve (YNNR). Meanwhile, a fully supervised classifier support vector machine (SVM) was tested in the two scenarios for comparison. With these scenarios, the crucial phenological stages and the advantage of phenological NDVI-TSA in S. alterniflora recognition were also investigated. Results indicated the EOCC using only positive training data performed similarly well with the SVM trained on complete training data in the YNNR. Moreover, the EOCC algorithm presented a more robust transferability with notably higher classification accuracy than the SVM when being transferred to a second site, without a second training. Furthermore, when combined with the phenological NDVI-TSA, the EOCC algorithm presented more balanced sensitivity–specificity result, showing slightly better transferability than it performed in the best phenological stage (i.e., senescence stage of November). The achieved results (overall accuracy (OA), Kappa, and true skill statistic (TSS) were 92.92%, 0.843, and 0.834 for the YNNR, and OA, Kappa, and TSS were 90.94%, 0.815, and 0.825 for transferability to the non-training site) suggest that our detection scheme has a high potential for the mapping of S. alterniflora across different areas, and the EOCC algorithm can be a viable alternative to traditional supervised classification method for invasive plant detection.

A heavy workload is required for sample collection for urban land use classification, and researchers are in urgent need of sampling strategies as a guide to achieve more effective work. In this paper, we make use of an urban land use survey to obtain a complete sample set of a city, test the impact of different training and validation sample sizes on the accuracy, and summarize the sampling strategy. The following conclusions are drawn based on our systematic analysis in Shenzhen. (1) For the best classification accuracy, the number of training samples should be no less than 40% of the total number of parcels or no less than 5500 parcels. For the best labor cost performance, the number should be no less than 7% or no less than 900. (2) The accuracy evaluation is stable and reliable and requires validation sample numbers of no less than 10% of the total or no less than 1200. (3) Samples with a purity of 60–90% are preferred, and the classification effectiveness is better in samples with a purity greater than 90% under the same number. (4) If spatial equilibrium sampling cannot be carried out, sampling areas with complex land use patterns should be preferred.

Seasonal dynamic land cover maps could provide useful information to ecosystem, water-resource and climate modelers. However, they are rarely mapped more frequent than annually. Here, we propose an approach to map dynamic land cover types with frequently available satellite data. Landsat 8 data acquired from nine dates over Beijing within a one-year period were used to map seasonal land cover dynamics. A two-step procedure was performed for training sample collection to get better results. Sample sets were interpreted for each acquisition date of Landsat 8 image. We used the random forest classifier to realize the mapping. Nine sets of experiments were designed to incorporate different input features and use of spatial temporal information into the dynamic land cover classification. Land cover maps obtained with single-date data in the optical spectral region were used as benchmarks. Texture, NDVI and thermal infrared bands were added as new features for improvements. A Markov random field (MRF) model was applied to maintain the spatio-temporal consistency. Classifications with all features from all images were performed, and an MRF model was also applied to the results estimated with all features. The best overall accuracies achieved for each date ranged from 75.31% to 85.61%.

Stand age distribution is an important descriptor of boreal forest structure, which is directly linked to many ecosystem processes including the carbon cycle, the land–atmosphere interaction and ecosystem services, among others. Almost half of the global boreal biome is located in Russia. The vast extent, remote location, and limited accessibility of Russian boreal forests make remote sensing the only feasible approach to characterize these forests to their full extent. A wide variety of satellite observations are currently available to monitor forest change and infer its structure, however, the period of observations is mostly limited to the 2000s era. Reconstruction of wall-to-wall maps of stand age distribution requires merging longer-term site observations of forest cover change available at the Landsat scale at a subset of locations in Russia with the wall-to-wall coverage available from coarse resolution satellites since 2000. This paper presents a dataset consisting of a suite of multi-year forest disturbance samples and samples of undisturbed forests across Russia derived from Landsat Thematic Mapper and Enhanced Thematic Mapper Plus images from 1985 to 2000. These samples provide crucial information regarding disturbance history in selected regions across the Russian boreal forest and are designed to serve as a training and/or validation dataset for coarse resolution data products. The overall accuracy and Kappa coefficient for the entire sample collection was found to be 83.98% and 0.83%, respectively. It is hoped that the presented dataset will benefit subsequent studies on a variety of aspects of the Russian boreal forest, especially in relation to the carbon budget and climate.

Land cover classification of urban areas is critical for understanding the urban environment. High-resolution remotely sensed imagery provides abundant, detailed spatial information for urban classification. In the meantime, OpenStreetMap (OSM) data, as typical crowd-sourced geographical information, have been an emerging data source for obtaining urban information. In this context, a land cover classification method that fuses high-resolution remotely sensed imagery and OSM data is proposed. Training samples were generated by integrating the OSM data and multiple information indexes. OSM data, which contain class attributes and location information of urban objects, served as the labels of initial training samples. Multiple information indexes that reflect spectral and spatial characteristics of different classes were utilized to improve the training set. Morphological attribute profiles were used because the structural and contextual information of images was effective in distinguishing the classes with similar spectral characteristics. Moreover, a road superimposition strategy that considers road hierarchy was developed because OSM data provide road information with high completeness in the urban area. Experiments were conducted on the data captured over Wuhan city, and three state-of-the-art approaches were adopted for comparison. Results show that the proposed approach obtains satisfactory results and outperforms the other comparative approaches.

There is a consensus about the necessity to achieve a quick soil spatial information with few human resources. Remote/proximal sensing and pedotransference are methods that can be integrated into this approach. On the other hand, there is still a lack of strategies indicating on how to put this in practice, especially in the tropics. Thus, the objective of this work was to suggest a strategy for the spatial prediction of soil classes by using soil spectroscopy from ground laboratory spectra to space images platform, as associated with terrain attributes and spectral libraries. The study area is located in São Paulo State, Brazil, which was covered by a regular grid (one per ha), with 473 boreholes collected at top and undersurface. All soil samples were analyzed in laboratory (granulometry and chemical), and scanned with a VIS-NIR-SWIR (400–2500 nm) spectroradiometer. We developed two traditional pedological maps with different detail levels for comparison: TFS-1 regarding orders and subgroups; and TFS-2 with additional information such as color, iron and fertility. Afterwards, we performed a digital soil map, generated by models, which used the following information: (i) predicted soil attributes from undersurface layer (diagnostic horizon), obtained by using a local spectral library; (ii) spectral reflectance of a bare soil surface obtained by Landsat image; and (iii) derivative of terrain attributes. Thus, the digital map was generated by a combination of three variables: remote sensing (Landsat data), proximal sensing (laboratory spectroscopy) and relief. Landsat image with bare soil was used as a first observation of surface. This strategy assisted on the location of topossequences to achieve soil variation in the area. Afterwards, spectral undersurface information from these locations was used to modelize soil attributes quantification (156 samples). The model was used to quantify samples in the entire area by spectra (other 317 samples). Since the surface was bare soil, it was sampled by image spectroscopy. Indeed, topsoil spectral laboratory information presented great similarity with satellite spectra. We observed angle variation on spectra from clayey to sandy soils as differentiated by intensity. Soil lines between bands 3/4 and 5/7 were helpful on the link between laboratory and satellite data. The spectral models of soil attributes (i.e., clay, sand, and iron) presented a high predictive performance (R2 0.71 to 0.90) with low error. The spatial prediction of these attributes also presented a high performance (validations with R2 > 0.78). The models increased spatial resolution of soil weathering information using a known spectral library. Elevation (altitude) improved mapping due to correlation with soil attributes (i.e., clay, iron and chemistry). We observed a close relationship between soil weathering index map and laboratory spectra + image spectra + relief parameters. The color composite of the 5R, 4G and 3B had great performance on the detection of soils along topossequences, since colors went from dark blue to light purple, and were related with soil texture and mineralogy of the region. The comparison between the traditional and digital soil maps showed a global accuracy of 69% for the TFS-1 map and 62% in the TFS-2, with kappa indices of 0.52 and 0.45, respectively. We randomly validated both digital and traditional maps with individual plots at field. We achieve a 75% and 80% agreement for digital and traditional maps, respectively, which allows us to conclude that traditional map is not necessarily the truth and digital is very close. The key of the strategy was to use bare soil image as a first step on the indication of soil variation in the area, indicating in-situ location for sample collection in all depths. The current strategy is innovative since we linked sensors from ground to space in addition with relief parameters and spectral libraries. The strategy indicates a more accurate map with less soil samples and lower cost.