The influence of window size on remote sensing-based prediction of forest structural variables

Abstract Background Determining the appropriate window size is a critical step in the estimation process of stand structural variables based on remote sensing data. Because the value of the reference laser and image metrics that affect the quality of the prediction model depends on window size. However, suitable window sizes are usually determined by trial and error. There are a limited number of published studies evaluating appropriate window sizes for different remote sensing data. This research investigated the effect of window size on predicting forest structural variables using airborne LiDAR data, digital aerial image and WorldView-3 satellite image. Results In the WorldView-3 and digital aerial image, significant differences were observed in the prediction accuracies of the structural variables according to different window sizes. For the estimation based on WorldView-3 in black pine stands, the optimal window sizes for stem number (N), volume (V), basal area (BA) and mean height (H) were determined as 1000 m2, 100 m2, 100 m2 and 600 m2, respectively. In oak stands, the R2 values of each moving window size were almost identical for N and BA. The optimal window size was 400 m2 for V and 600 m2 for H. For the estimation based on aerial image in black pine stands, the 800 m2 window size was optimal for N and H, the 600 m2 window size was optimal for V and the 1000 m2 window size was optimal for BA. In the oak stands, the optimal window sizes for N, V, BA and H were determined as 1000 m2, 100 m2, 100 m2 and 600 m2, respectively. The optimal window sizes may need to be scaled up or down to match the stand canopy components. In the LiDAR data, the R2 values of each window size were almost identical for all variables of the black pine and the oak stands. Conclusion This study illustrated that the window size has an effect on the prediction accuracy in estimating forest structural variables based on remote sensing data. Moreover, the results showed that the optimal window size for forest structural variables varies according to remote sensing data and tree species composition.

Download Full-text

The Influence of Widow Size on Remote Sensing-Based Prediction of Forest Structural Variables

10.21203/rs.3.rs-236373/v1 ◽

2021 ◽

Author(s):

Ulaş Yunus ÖZKAN ◽

Tufan Demirel

Keyword(s):

Remote Sensing ◽

Remote Sensing Data ◽

Window Size ◽

Aerial Image ◽

Lidar Data ◽

Black Pine ◽

Sensing Data ◽

Structural Variables ◽

Pine Stands ◽

Optimal Window

Abstract Background: Determining the appropriate window size is a critical step for estimating stand structural variables based on remote sensing data. Because the value of the reference laser and image metrics that affect the quality of the prediction model depends on window size. However, suitable window sizes are usually determined by trial and error. There are a limited number of published studies evaluating appropriate window sizes for different remote sensing data. This research investigated the effect of window size on predicting forest structural variables using airborne LiDAR data, digital aerial image and WorldView-3 satellite image.Results: In the WorldView-3 and digital aerial image, significant differences were observed in the prediction accuracies of the structural variables according to different window sizes. For the estimation based on WorldView-3 in black pine stands, the optimal window sizes for stem number (N), volume (V), basal area (BA) and mean height (H) were determined as 1000 m2, 100 m2, 100 m2 and 600 m2, respectively. In oak stands, the R2 values of each moving window size were almost identical for N and BA. The optimal window size was 400 m2 for V and 600 m2 for H. For the estimation based on aerial image in black pine stands, the 800 m2 window size is optimal for N and H, the 600 m2 window size is optimal for V and the 1000 m2 window size is optimal for BA. In the oak stands, the optimal window sizes for N, V, BA and H were determined as 1000 m2, 100 m2, 100 m2 and 600 m2, respectively. The optimal window sizes may need to be scaled up or down to match the stand canopy components. In the LiDAR data, the R2 values of each window size were almost identical for all variables of the black pine and the oak stands.Conclusion: This study illustrated that the window size has an effect on the prediction accuracy in estimating forest structural variables based on remote sensing data. Moreover, the results showed that the optimal window size for forest structural variables varies according to remote sensing data and tree species composition.

Download Full-text

Mapping the Urban Atmospheric Carbon Stock by LiDAR and WorldView-3 Data

Forests ◽

10.3390/f12060692 ◽

2021 ◽

Vol 12 (6) ◽

pp. 692

Author(s):

MD Abdul Mueed Choudhury ◽

Ernesto Marcheggiani ◽

Andrea Galli ◽

Giuseppe Modica ◽

Ben Somers

Keyword(s):

Remote Sensing ◽

Urban Area ◽

Tree Species ◽

Carbon Stock ◽

Dominant Species ◽

Remote Sensing Data ◽

Data Sources ◽

Lidar Data ◽

Urban Tree ◽

Sensing Data

Currently, the worsening impacts of urbanizations have been impelled to the importance of monitoring and management of existing urban trees, securing sustainable use of the available green spaces. Urban tree species identification and evaluation of their roles in atmospheric Carbon Stock (CS) are still among the prime concerns for city planners regarding initiating a convenient and easily adaptive urban green planning and management system. A detailed methodology on the urban tree carbon stock calibration and mapping was conducted in the urban area of Brussels, Belgium. A comparative analysis of the mapping outcomes was assessed to define the convenience and efficiency of two different remote sensing data sources, Light Detection and Ranging (LiDAR) and WorldView-3 (WV-3), in a unique urban area. The mapping results were validated against field estimated carbon stocks. At the initial stage, dominant tree species were identified and classified using the high-resolution WorldView3 image, leading to the final carbon stock mapping based on the dominant species. An object-based image analysis approach was employed to attain an overall accuracy (OA) of 71% during the classification of the dominant species. The field estimations of carbon stock for each plot were done utilizing an allometric model based on the field tree dendrometric data. Later based on the correlation among the field data and the variables (i.e., Normalized Difference Vegetation Index, NDVI and Crown Height Model, CHM) extracted from the available remote sensing data, the carbon stock mapping and validation had been done in a GIS environment. The calibrated NDVI and CHM had been used to compute possible carbon stock in either case of the WV-3 image and LiDAR data, respectively. A comparative discussion has been introduced to bring out the issues, especially for the developing countries, where WV-3 data could be a better solution over the hardly available LiDAR data. This study could assist city planners in understanding and deciding the applicability of remote sensing data sources based on their availability and the level of expediency, ensuring a sustainable urban green management system.

Download Full-text

Comparison of Machine Learning Algorithms for Wildland-Urban Interface Fuelbreak Planning Integrating ALS and UAV-Borne LiDAR Data and Multispectral Images

Drones ◽

10.3390/drones4020021 ◽

2020 ◽

Vol 4 (2) ◽

pp. 21 ◽

Cited By ~ 1

Author(s):

Francisco Rodríguez-Puerta ◽

Rafael Alonso Ponce ◽

Fernando Pérez-Rodríguez ◽

Beatriz Águeda ◽

Saray Martín-García ◽

...

Keyword(s):

Machine Learning ◽

Remote Sensing ◽

Random Forest ◽

Learning Algorithms ◽

Remote Sensing Data ◽

Machine Learning Algorithms ◽

Data Sources ◽

Lidar Data ◽

Sensing Data ◽

Sentinel 2

Controlling vegetation fuels around human settlements is a crucial strategy for reducing fire severity in forests, buildings and infrastructure, as well as protecting human lives. Each country has its own regulations in this respect, but they all have in common that by reducing fuel load, we in turn reduce the intensity and severity of the fire. The use of Unmanned Aerial Vehicles (UAV)-acquired data combined with other passive and active remote sensing data has the greatest performance to planning Wildland-Urban Interface (WUI) fuelbreak through machine learning algorithms. Nine remote sensing data sources (active and passive) and four supervised classification algorithms (Random Forest, Linear and Radial Support Vector Machine and Artificial Neural Networks) were tested to classify five fuel-area types. We used very high-density Light Detection and Ranging (LiDAR) data acquired by UAV (154 returns·m−2 and ortho-mosaic of 5-cm pixel), multispectral data from the satellites Pleiades-1B and Sentinel-2, and low-density LiDAR data acquired by Airborne Laser Scanning (ALS) (0.5 returns·m−2, ortho-mosaic of 25 cm pixels). Through the Variable Selection Using Random Forest (VSURF) procedure, a pre-selection of final variables was carried out to train the model. The four algorithms were compared, and it was concluded that the differences among them in overall accuracy (OA) on training datasets were negligible. Although the highest accuracy in the training step was obtained in SVML (OA=94.46%) and in testing in ANN (OA=91.91%), Random Forest was considered to be the most reliable algorithm, since it produced more consistent predictions due to the smaller differences between training and testing performance. Using a combination of Sentinel-2 and the two LiDAR data (UAV and ALS), Random Forest obtained an OA of 90.66% in training and of 91.80% in testing datasets. The differences in accuracy between the data sources used are much greater than between algorithms. LiDAR growth metrics calculated using point clouds in different dates and multispectral information from different seasons of the year are the most important variables in the classification. Our results support the essential role of UAVs in fuelbreak planning and management and thus, in the prevention of forest fires.

Download Full-text

Hierarchical Geographic Object-Based Vegetation Type Extraction Based on Multi-Source Remote Sensing Data

Forests ◽

10.3390/f11121271 ◽

2020 ◽

Vol 11 (12) ◽

pp. 1271

Author(s):

Xuegang Mao ◽

Yueqing Deng ◽

Liang Zhu ◽

Yao Yao

Keyword(s):

Remote Sensing ◽

Forest Type ◽

Vegetation Type ◽

Remote Sensing Data ◽

Airborne Lidar ◽

Lidar Data ◽

Sensing Data ◽

Object Based ◽

Four Levels ◽

Airborne Lidar Data

Providing vegetation type information with accurate surface distribution is one of the important tasks of remote sensing of the ecological environment. Many studies have explored ecosystem structure information at specific spatial scales based on specific remote sensing data, but it is still rare to extract vegetation information at various landscape levels from a variety of remote sensing data. Based on Gaofen-1 satellite (GF-1) Wide-Field-View (WFV) data (16 m), Ziyuan-3 satellite (ZY-3) and airborne LiDAR data, this study comparatively analyzed the four levels of vegetation information by using the geographic object-based image analysis method (GEOBIA) on the typical natural secondary forest in Northeast China. The four levels of vegetation information include vegetation/non-vegetation (L1), vegetation type (L2), forest type (L3) and canopy and canopy gap (L4). The results showed that vegetation height and density provided by airborne LiDAR data could extract vegetation features and categories more effectively than the spectral information provided by GF-1 and ZY-3 images. Only 0.5 m LiDAR data can extract four levels of vegetation information (L1–L4); and from L1 to L4, the total accuracy of the classification decreased orderly 98%, 93%, 80% and 69%. Comparing with 2.1 m ZY-3, the total classification accuracy of L1, L2 and L3 extracted by 2.1 m LiDAR data increased by 3%, 17% and 43%, respectively. At the vegetation/non-vegetation level, the spatial resolution of data plays a leading role, and the data types used at the vegetation type and forest type level become the main influencing factors. This study will provide reference for data selection and mapping strategies for hierarchical multi-scale vegetation type extraction.

Download Full-text

Remote sensing of terrestrial non-photosynthetic vegetation using hyperspectral, multispectral, SAR, and LiDAR data

Progress in Physical Geography Earth and Environment ◽

10.1177/0309133315582005 ◽

2015 ◽

Vol 40 (2) ◽

pp. 276-304 ◽

Cited By ~ 24

Author(s):

Zhaoqin Li ◽

Xulin Guo

Keyword(s):

Remote Sensing ◽

Remote Sensing Data ◽

Wildlife Habitat ◽

Optical Data ◽

Lidar Data ◽

Natural Fire ◽

Sensing Data ◽

Advantages And Disadvantages ◽

Sar Data ◽

Ecological Importance

Quantifying non-photosynthetic vegetation (NPV) is important for ecosystem management and studies on climate change, ecology, and hydrology because it controls uptake of carbon, water, and nutrients together with frequency and intensity of natural fire, and serves as wildlife habitat. The ecological importance of NPV has driven considerable research on quantitatively estimating NPV in diverse ecosystems including croplands, forests, grasslands, savannah, and shrublands using remote sensing data. However, a comprehensive review is not available. This review highlights the theoretical bases and the critical elements of remote sensing for NPV estimation, and summarizes research on estimating fractional cover of NPV (NPV cover) and biomass using passive optical hyperspectral and multispectral remote sensing data, active synthetic aperture radar (SAR) and light detection and ranging (LiDAR), and integrated multi-sensorial data. We also discuss advantages and disadvantages of optical, LiDAR, and SAR data and pinpoint future direction on NPV estimation using remote sensing data. Currently, most NPV research has been mainly focused on NPV cover, not NPV biomass, using passive optical data, while a few studies have used LiDAR data to quantify NPV biomass in forests and SAR data on NPV estimation in croplands and grasslands. In the future, more efforts should be made to estimate NPV biomass and to investigate the best use of hyperspectral, LiDAR, SAR data, and their integration. The upcoming new optical sensor on Sentinel-2 satellites, Radarsat-2 constellation and NovaSAR, technological innovation in hyperspectral, LiDAR, and SAR, and improvements on methodology for information extraction and combining multi-sensorial data will provide more opportunities for NPV estimation.

Download Full-text

LiDAR, UAV SfM and geomorphic change detection in small quarry and landslide interactions

10.5194/egusphere-egu21-14651 ◽

2021 ◽

Author(s):

Mihai Cosmin Ciotină ◽

Mihai Niculiță ◽

Valeriu Stoilov-Linu

Keyword(s):

Remote Sensing ◽

Change Detection ◽

Rural Areas ◽

Construction Projects ◽

Remote Sensing Data ◽

The Body ◽

Lidar Data ◽

Clay Material ◽

Sensing Data ◽

Geomorphic Change Detection

<p>Quarry activity triggers landslides, especially in small, unplanned, and not maintained quarries. Given the size of these small quarries that are very frequent in the rural areas of north-eastern Romania, their study is difficult because of the lack of topographic data. We show the usage of remote sensing data for geomorphic change detection, which is able to reveal the topographic evolution of the quarrying and landsliding. Legacy LiDAR data from 2012 and field surveyed UAV from 2019 are used to assess the topographic changes, compared to the 1980 5k topographic maps. The quarry location is related to the presence of old landslide bodies (dated to the early medieval period using radiocarbon ages of soil organic matter fractions), from which the clay material is excavated for various construction projects. The unplanned excavation reactivated the body of an old landslide that will continue evolving. The usage of LiDAR data and the UAV SfM survey allowed us to derive 0.25 m DEMS that pinpoint the volumetric change of the quarried material and of the landslide reactivation. As a future prospect, the use of such remote sensing data can pinpoint areas where these unplanned quarries could affect the stability of the hillslopes and become a hazard.</p>

Download Full-text

CROWN-LEVEL TREE SPECIES CLASSIFICATION USING INTEGRATED AIRBORNE HYPERSPECTRAL AND LIDAR REMOTE SENSING DATA

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-3-2629-2018 ◽

2018 ◽

Vol XLII-3 ◽

pp. 2629-2634

Author(s):

Z. Wang ◽

J. Wu ◽

Y. Wang ◽

X. Kong ◽

H. Bao ◽

...

Keyword(s):

Remote Sensing ◽

Tree Species ◽

Remote Sensing Data ◽

Lidar Data ◽

Tree Crown ◽

Species Classification ◽

Individual Tree ◽

Sensing Data ◽

Tree Species Classification ◽

Shape Characteristics

Mapping tree species is essential for sustainable planning as well as to improve our understanding of the role of different trees as different ecological service. However, crown-level tree species automatic classification is a challenging task due to the spectral similarity among diversified tree species, fine-scale spatial variation, shadow, and underlying objects within a crown. Advanced remote sensing data such as airborne Light Detection and Ranging (LiDAR) and hyperspectral imagery offer a great potential opportunity to derive crown spectral, structure and canopy physiological information at the individual crown scale, which can be useful for mapping tree species. In this paper, an innovative approach was developed for tree species classification at the crown level. The method utilized LiDAR data for individual tree crown delineation and morphological structure extraction, and Compact Airborne Spectrographic Imager (CASI) hyperspectral imagery for pure crown-scale spectral extraction. Specifically, four steps were include: 1) A weighted mean filtering method was developed to improve the accuracy of the smoothed Canopy Height Model (CHM) derived from LiDAR data; 2) The marker-controlled watershed segmentation algorithm was, therefore, also employed to delineate the tree-level canopy from the CHM image in this study, and then individual tree height and tree crown were calculated according to the delineated crown; 3) Spectral features within 3&thinsp;&times;&thinsp;3 neighborhood regions centered on the treetops detected by the treetop detection algorithm were derived from the spectrally normalized CASI imagery; 4) The shape characteristics related to their crown diameters and heights were established, and different crown-level tree species were classified using the combination of spectral and shape characteristics. Analysis of results suggests that the developed classification strategy in this paper (OA&thinsp;=&thinsp;85.12&thinsp;%, Kc&thinsp;=&thinsp;0.90) performed better than LiDAR-metrics method (OA&thinsp;=&thinsp;79.86&thinsp;%, Kc&thinsp;=&thinsp;0.81) and spectral-metircs method (OA&thinsp;=&thinsp;71.26, Kc&thinsp;=&thinsp;0.69) in terms of classification accuracy, which indicated that the advanced method of data processing and sensitive feature selection are critical for improving the accuracy of crown-level tree species classification.

Download Full-text