Above-ground biomass (AGB) directly relates to the productivity of forests. Precisely, AGB mapping for regional forests based on very high resolution (VHR) imagery is widely needed for evaluation of productivity. However, the diversity of variables and algorithms and the difficulties inherent in high resolution optical imagery make it complex. In this paper, we explored the potentials of the state-of-art algorithm convolutional neural networks (CNNs), which are widely used for its high-level representation, but rarely applied for AGB estimation. Four experiments were carried out to compare the performance of CNNs and other state-of-art Machine Learning (ML) algorithms: (1) performance of CNN using bands, (2) performance of Random Forest (RF), support vector regression (SVR), artificial neural network (ANN) on bands, and vegetation indices (VIs). (3) Performance of RF, SVR, and ANN on gray-level co-occurrence matrices (GLCM), and exploratory spatial data analysis (ESDA), and (4) performance of RF, SVR, and ANN based on all combined data and ESDA+VIs. CNNs reached satisfactory results (with R2 = 0.943) even with limited input variables (i.e., only bands). In comparison, RF and SVR with elaborately designed data obtained slightly better accuracy than CNN. For examples, RF based on GLCM textures reached an R2 of 0.979 and RF based on all combined data reached a close R2 of 0.974. However, the results of ANN were much worse (with the best R2 of 0.885).
The subtropical vegetation plays an important role in maintaining the structure and function of global ecosystems, and its contribution to the global carbon balance are receiving increasing attention. The fractional vegetation cover (FVC) as an important indicator for monitoring environment change, is widely used to analyze the spatiotemporal pattern of regional and even global vegetation. China is an important distribution area of subtropical vegetation. Therefore, we first used the dimidiate pixel model to extract the subtropical FVC of China during 2001-2018 based on MODIS land surface reflectance data, and then used the linear regression analysis and the variation coefficient to explore its spatiotemporal variations characteristics. Finally, the partial correlation analysis and the partial derivative model were used to analyze the influences and contributions of climate factors on FVC, respectively. The results showed that (1) the subtropical FVC had obvious spatiotemporal heterogeneity; the FVC high-coverage and medium-coverage zones were concentratedly and their combined area accounted for more than 70% of the total study area. (2) The interannual variation in the average subtropical FVC from 2001 to 2018 showed a significant growth trend. (3) In 76.28% of the study area, the regional FVC showed an increasing trend, and the remaining regional FVC showed a decreasing trend. However, the overall fluctuations in the FVC (increasing or decreasing) in the region were relatively stable. (4) The influences of climate factors to the FVC exhibited obvious spatial differences. More than half of all pixels exhibited the influence of the average annual minimum temperature and the annual precipitation had positive on FVC, while the average annual maximum temperature had negative on FVC. (5) The contributions of climate changes to FVC had obvious heterogeneity, and the average annual minimum temperature was the main contribution factor affecting the dynamic variations of FVC.
Dynamic monitoring of carbon storage in forests resources is important for tracking ecosystem functionalities and climate change impacts. In this study, we used multi-year Landsat data combined with a Random Forest (RF) algorithm to estimate the forest aboveground carbon (AGC) in a forest area in China (Hang-Jia-Hu) and analyzed its spatiotemporal changes during the past two decades. Maximum likelihood classification was applied to make land-use maps. Remote sensing variables, such as the spectral band, vegetation indices, and derived texture features, were extracted from 20 Landsat TM and OLI images over five different years (2000, 2004, 2010, 2015, and 2018). These variables were subsequently selected according to their importance and subsequently used in the RF algorithm to build an estimation model of forest AGC. The results showed the following: (1) Verification of classification results showed maximum likelihood can extract land information effectively. Our land cover classification yielded overall accuracies between 86.86% and 89.47%. (2) Additionally, our RF models showed good performance in predicting forest AGC, with R2 from 0.65 to 0.73 in the training and testing phase and a RMSE range between 3.18 and 6.66 Mg/ha. RMSEr in the testing phase ranged from 20.27 to 22.27 with a low model error. (3) The estimation results indicated that forest AGC in the past two decades increased with density at 10.14 Mg/ha, 21.63 Mg/ha, 26.39 Mg/ha, 29.25 Mg/ha, and 44.59 Mg/ha in 2000, 2004, 2010, 2015, and 2018. The total forest AGC storage had a growth rate of 285%. (4) Our study showed that, although forest area decreased in the study area during the time period under study, the total forest AGC increased due to an increment in forest AGC density. However, such an effect is overridden in the vicinity of cities by intense urbanization and the loss of forest covers. Our study demonstrated that the combined use of remote sensing data and machine learning techniques can improve our ability to track the forest changes in support of regional natural resource management practices.
Analysis of urban land use dynamics is essential for assessing ecosystem functionalities and climate change impacts. The focus of this study is on monitoring the characteristics of urban expansion in Hang-Jia-Hu and evaluating its influences on forests by applying 30-m multispectral Landsat data and a machine learning algorithm. Firstly, remote sensed images were preprocessed with radiation calibration, atmospheric correction and topographic correction. Then, the C5.0 decision tree was used to establish classification trees and then applied to make land use maps. Finally, spatiotemporal changes were analyzed through dynamic degree and land use transfer matrix. In addition, average land use transfer probability matrix (ATPM) was utilized for the prediction of land use area in the next 20 years. The results show that: (1) C5.0 decision tree performed with precise accuracy in land use classification, with an average total accuracy and kappa coefficient of more than 90.04% and 0.87. (2) During the last 20 years, land use in Hang-Jia-Hu has changed extensively. Urban area expanded from 5.84% in 1995 to 21.32% in 2015, which has brought about enormous impacts on cultivated land, with 198,854 hectares becoming urban, followed by forests with 19,823 hectares. (3) Land use area prediction based on the ATPM revealed that urbanization will continue to expand at the expense of cultivated land, but the impact on the forests will be greater than the past two decades. Rationality of urban land structure distribution is important for economic and social development. Therefore, remotely sensed technology combined with machine learning algorithms is of great significance to the dynamic detection of resources in the process of urbanization.
The application of deep learning techniques, especially deep convolutional neural networks (DCNNs), in the intelligent mapping of very high spatial resolution (VHSR) remote sensing images has drawn much attention in the remote sensing community. However, the fragmented distribution of urban land use types and the complex structure of urban forests bring about a variety of challenges for urban land use mapping and the extraction of urban forests. Based on the DCNN algorithm, this study proposes a novel object-based U-net-DenseNet-coupled network (OUDN) method to realize urban land use mapping and the accurate extraction of urban forests. The proposed OUDN has three parts: the first part involves the coupling of the improved U-net and DenseNet architectures; then, the network is trained according to the labeled data sets, and the land use information in the study area is classified; the final part fuses the object boundary information obtained by object-based multiresolution segmentation into the classification layer, and a voting method is applied to optimize the classification results. The results show that (1) the classification results of the OUDN algorithm are better than those of U-net and DenseNet, and the average classification accuracy is 92.9%, an increase in approximately 3%; (2) for the U-net-DenseNet-coupled network (UDN) and OUDN, the urban forest extraction accuracies are higher than those of U-net and DenseNet, and the OUDN effectively alleviates the classification error caused by the fragmentation of urban distribution by combining object-based multiresolution segmentation features, making the overall accuracy (OA) of urban land use classification and the extraction accuracy of urban forests superior to those of the UDN algorithm; (3) based on the Spe-Texture (the spectral features combined with the texture features), the OA of the OUDN in the extraction of urban land use categories can reach 93.8%, thereby the algorithm achieved the accurate discrimination of different land use types, especially urban forests (99.7%). Therefore, this study provides a reference for feature setting for the mapping of urban land use information from VHSR imagery.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.