GLORIA

GEOMAR Library Ocean Research Information Access

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
  • 1
    Online Resource
    Online Resource
    Institute of Electrical and Electronics Engineers (IEEE) ; 2020
    In:  IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Vol. 13 ( 2020), p. 113-128
    In: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Institute of Electrical and Electronics Engineers (IEEE), Vol. 13 ( 2020), p. 113-128
    Type of Medium: Online Resource
    ISSN: 1939-1404 , 2151-1535
    Language: Unknown
    Publisher: Institute of Electrical and Electronics Engineers (IEEE)
    Publication Date: 2020
    detail.hit.zdb_id: 2457423-5
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
  • 2
    In: Land Degradation & Development, Wiley, Vol. 31, No. 8 ( 2020-05-15), p. 939-958
    Abstract: Properly mapping the sustainability of bamboo forest production plays an important role in providing basic strategies for decision makers to ensure sustainable use of bamboo resources. Understanding the response pattern of drought, poor management, elevation, and barren soil to bamboo forest ecosystem productivity is critical to formulating appropriate improvement strategies of sustainable management of bamboo forest productivity for addressing growing challenges of bamboo forest land degradation. The objectives of this study were to quantify differences in productivity, meteorological, topographical, soil, and bamboo distribution and structure factors under different sustainable management levels of bamboo forest ecosystem productivity in order to support management decision making in a spatiotemporally explicit context. We constructed an innovative three‐layer index system for the sustainable management of bamboo forest productivity by integrating productivity, meteorological, soil, topographic, bamboo distribution, and structure factors to promote sustainable management and spatiotemporal decision making, particularly in bamboo forest areas with low productivity. The partial least squares (PLS) path model was used to analyze the spatiotemporal effects of different factors on bamboo forest productivity and to create sustainable management maps that could be used for spatially informed decision making regarding bamboo forest production. The results showed the spatial and temporal variations in gross primary productivity (GPP), net primary productivity (NPP), and net ecosystem exchange (NEE) in bamboo forests. The sustainable management index was also mapped each year throughout the study area. We divided the index value range into five management‐friendly classes, which were shown to be directly related to GPP, NPP, NEE, Slope, Aspect, soil texture, hydrolytic nitrogen, and Abundance. We found that the areas with relatively high sustainable management levels (I and II) occupied only 18.94% of the bamboo forest area and exhibited a highly clustered distribution. Most of the other areas (78.67%) had relatively low levels of sustainable management (III and IV), and their distribution was rather scattered. The remaining 2.39% of the bamboo forest area that had the lowest sustainable management level (V) was small in area, fragmented, and not conducive to intensive management. The results of the present study can serve as a useful reference for bamboo forest management, which is of great importance for bamboo‐based ecosystems and economies.
    Type of Medium: Online Resource
    ISSN: 1085-3278 , 1099-145X
    URL: Issue
    Language: English
    Publisher: Wiley
    Publication Date: 2020
    detail.hit.zdb_id: 2021787-0
    detail.hit.zdb_id: 1319202-4
    SSG: 14
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
  • 3
    Online Resource
    Online Resource
    American Association for the Advancement of Science (AAAS) ; 2023
    In:  Journal of Remote Sensing Vol. 3 ( 2023-01)
    In: Journal of Remote Sensing, American Association for the Advancement of Science (AAAS), Vol. 3 ( 2023-01)
    Abstract: Estimating potential height of forests is one of key tasks in forest restoration planning. Since regional maximum height statistics is difficult to account for local heterogeneity, biotic and abiotic mechanism-based methods are required. Different from the mainstream models that possesses either hydraulic constraint or mechanical constraint, we used a more lightweight model based on balance of water availability and consumption, named the Allometric Scaling and Resource Limitations model. Several enhancements were added, making up the third version of the model, and we deployed it using Google Earth Engine (GEE). A map of potential tree height at 90-m resolution is created for beech–maple–birch forests in northeastern United States. Within the oldest forests among the study area, the model reproduces the tree height level of ~25 m with root mean square deviation (RMSD) of 3.71 m from a high-resolution product of canopy height estimates. Under a threshold of 20% deviation, 82.9% of pixels agree with the existing tree heights. Outside of the oldest forests, RMSD raises to 5.01 m, and agreement drops to 75.3%. Over the entire study area, 6.6% total pixels of interest have a predicted height below the current level. A total of 16.7% pixels have larger predictions relative to existing forest heights, with a half of them classified as mistakes of overestimation. Errors may come from uncertainty in climate reanalysis data and inadequate shading effects modeling. Our work confirms the applicability of this lightweight model for this static prediction task and explores the deployment of ecological mechanism-based models on the GEE platform.
    Type of Medium: Online Resource
    ISSN: 2694-1589
    Language: English
    Publisher: American Association for the Advancement of Science (AAAS)
    Publication Date: 2023
    detail.hit.zdb_id: 3060865-X
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
  • 4
    In: ISPRS International Journal of Geo-Information, MDPI AG, Vol. 9, No. 2 ( 2020-01-21), p. 64-
    Abstract: 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.
    Type of Medium: Online Resource
    ISSN: 2220-9964
    Language: English
    Publisher: MDPI AG
    Publication Date: 2020
    detail.hit.zdb_id: 2655790-3
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
  • 5
    Online Resource
    Online Resource
    Shanghai Institute of Optics and Fine Mechanics ; 2020
    In:  Laser & Optoelectronics Progress Vol. 57, No. 10 ( 2020), p. 101001-
    In: Laser & Optoelectronics Progress, Shanghai Institute of Optics and Fine Mechanics, Vol. 57, No. 10 ( 2020), p. 101001-
    Type of Medium: Online Resource
    ISSN: 1006-4125
    Uniform Title: 基于FCN的无人机可见光影像树种分类
    URL: Issue
    Language: English , Chinese
    Publisher: Shanghai Institute of Optics and Fine Mechanics
    Publication Date: 2020
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
  • 6
    In: Remote Sensing, MDPI AG, Vol. 12, No. 6 ( 2020-03-16), p. 958-
    Abstract: 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).
    Type of Medium: Online Resource
    ISSN: 2072-4292
    Language: English
    Publisher: MDPI AG
    Publication Date: 2020
    detail.hit.zdb_id: 2513863-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...