scholarly journals Combination of Multi-Temporal Sentinel 2 Images and Aerial Image Based Canopy Height Models for Timber Volume Modelling

Forests ◽  
2019 ◽  
Vol 10 (9) ◽  
pp. 746 ◽  
Author(s):  
Johannes Schumacher ◽  
Margret Rattay ◽  
Melanie Kirchhöfer ◽  
Petra Adler ◽  
Gerald Kändler
Keyword(s):  
Forest Inventory ◽  
Point Clouds ◽  
Support Vector ◽  
Timber Volume ◽  
Volume Model ◽  
Broadleaf Tree ◽  
Multi Temporal ◽  
Conifer Trees ◽  
Volume Models ◽  
Sentinel 2

Multi-temporal Sentinel 2 optical images and 3D photogrammetric point clouds can be combined to enhance the accuracy of timber volume models on large spatial scale. Information on the proportion of broadleaf and conifer trees improves timber volume models obtained from 3D photogrammetric point clouds. However, the broadleaf-conifer information cannot be obtained from photogrammetric point clouds alone. Furthermore, spectral information of aerial images is too inconsistent to be used for automatic broadleaf-conifer classification over larger areas. In this study we combined multi-temporal Sentinel 2 optical satellite images, 3D photogrammetric point clouds from digital aerial stereo photographs, and forest inventory plots representing an area of 35,751 km2 in south-west Germany for (1) modelling the percentage of broadleaf tree volume (BL%) using Sentinel 2 time series and (2) modelling timber volume per hectare using 3D photogrammetric point clouds. Forest inventory plots were surveyed in the same years and regions as stereo photographs were acquired (2013–2017), resulting in 11,554 plots. Sentinel 2 images from 2016 and 2017 were corrected for topographic and atmospheric influences and combined with the same forest inventory plots. Spectral variables from corrected multi-temporal Sentinel 2 images were calculated, and Support Vector Machine (SVM) regressions were fitted for each Sentinel 2 scene estimating the BL% for corresponding inventory plots. Variables from the photogrammetric point clouds were calculated for each inventory plot and a non-linear regression model predicting timber volume per hectare was fitted. Each SVM regression and the timber volume model were evaluated using ten-fold cross-validation (CV). The SVM regression models estimating the BL% per Sentinel 2 scene achieved overall accuracies of 68%–75% and a Root Mean Squared Error (RMSE) of 21.5–26.1. The timber volume model showed a RMSE% of 31.7%, a mean bias of 0.2%, and a pseudo-R2 of 0.64. Application of the SVM regressions on Sentinel 2 scenes covering the state of Baden-Württemberg resulted in predictions of broadleaf tree percentages for the entire state. These predicted values were used as additional predictor in the timber volume model, allowing for predictions of timber volume for the same area. Spatially high-resolution information about growing stock is of great practical relevance for forest management planning, especially when the timber volume of a smaller unit is of interest, for example of a forest stand or a forest district where not enough terrestrial inventory plots are available to make reliable estimations. Here, predictions from remote-sensing based models can be used. Furthermore, information about broadleaf and conifer trees improves timber volume models and reduces model errors and, thereby, prediction uncertainties.

scholarly journals Integration of UAV, Sentinel-1, and Sentinel-2 Data for Mangrove Plantation Aboveground Biomass Monitoring in Senegal

2019 ◽  
Vol 11 (1) ◽  
pp. 77 ◽  
Author(s):  
José Antonio Navarro ◽  
Nur Algeet ◽  
Alfredo Fernández-Landa ◽  
Jessica Esteban ◽  
Pablo Rodríguez-Noriega ◽  
...  
Keyword(s):  
Aboveground Biomass ◽  
Auxiliary Information ◽  
Field Measurements ◽  
Cost Effective ◽  
Point Clouds ◽  
Support Vector ◽  
Monitoring Methods ◽  
Individual Tree ◽  
Entire Study ◽  
Sentinel 2

Due to the increasing importance of mangroves in climate change mitigation projects, more accurate and cost-effective aboveground biomass (AGB) monitoring methods are required. However, field measurements of AGB may be a challenge because of their remote location and the difficulty to walk in these areas. This study is based on the Livelihoods Fund Oceanium project that monitors 10,000 ha of mangrove plantations. In a first step, the possibility of replacing traditional field measurements of sample plots in a young mangrove plantation by a semiautomatic processing of UAV-based photogrammetric point clouds was assessed. In a second step, Sentinel-1 radar and Sentinel-2 optical imagery were used as auxiliary information to estimate AGB and its variance for the entire study area under a model-assisted framework. AGB was measured using UAV imagery in a total of 95 sample plots. UAV plot data was used in combination with non-parametric support vector regression (SVR) models for the estimation of the study area AGB using model-assisted estimators. Purely UAV-based AGB estimates and their associated standard error (SE) were compared with model-assisted estimates using (1) Sentinel-1, (2) Sentinel-2, and (3) a combination of Sentinel-1 and Sentinel-2 data as auxiliary information. The validation of the UAV-based individual tree height and crown diameter measurements showed a root mean square error (RMSE) of 0.21 m and 0.32 m, respectively. Relative efficiency of the three model-assisted scenarios ranged between 1.61 and 2.15. Although all SVR models improved the efficiency of the monitoring over UAV-based estimates, the best results were achieved when a combination of Sentinel-1 and Sentinel-2 data was used. Results indicated that the methodology used in this research can provide accurate and cost-effective estimates of AGB in young mangrove plantations.

scholarly journals ALS-based wood volume models of forest stands and comparison with forest inventory data

2016 ◽  
Vol 64 (1) ◽  
pp. 5-16 ◽  
Author(s):  
Tauri Arumäe ◽  
Mait Lang
Keyword(s):  
Forest Inventory ◽  
Laser Scanning ◽  
Canopy Cover ◽  
Point Clouds ◽  
Test Site ◽  
Sample Plot ◽  
Volume Estimate ◽  
Wood Volume ◽  
Level Model ◽  
Volume Models

Abstract Airborne laser scanning (ALS) based standing wood volume models were analysed in two contrasting test sites with different forest types in Estonia. In Aegviidu test site main tree species are Scots pine and Norway spruce and Laeva test site is mainly dominated by deciduous species. ALS data measurements were carried out for Aegviidu in 2008 and for Laeva in 2013. Approximately 450 sample plots were established additionally to the forest inventory dataset in both test sites. Exclusive to the sample plots, 46 stands were measured in 2012 in Aegviidu for stand level model. The sample plot-based model standard error in Aegviidu was Se = 59.8 m3/ha (22%) and in Laeva Se = 69.2 m3/ha (29%). The stand-level model based on 46 measured stands from Aegviidu had Se = 38.4 m3/ha. Based on the models a cross-validation between the two test sites was carried out and systematic differences between the two test sites were found. The reasons are related to differences in optical properties of trees, crown shapes, flight configuration and canopy cover even though the sample plot based models included ALS-based canopy cover variable. The ALS-based wood volume estimate was also compared to forest inventory (FI) data and systematically larger estimates compared to FI dataset in both test sites were found. This average systematic error increased substantially (by 100 m3/ha) for stands with volume over 250 m3/ha. It was also detected that a model developed on small point clouds drawn for sample plots may produce systematic errors when applied to stand-level point clouds.

scholarly journals Multi-Temporal Sentinel-2 Data in Classification of Mountain Vegetation

2020 ◽  
Vol 12 (17) ◽  
pp. 2696 ◽  
Author(s):  
Martyna Wakulińska ◽  
Adriana Marcinkowska-Ochtyra
Keyword(s):  
National Parks ◽  
Vegetation Indices ◽  
European Space Agency ◽  
Principal Component ◽  
Support Vector ◽  
Electromagnetic Spectrum ◽  
Vegetation Monitoring ◽  
Multi Temporal ◽  
Mountain Vegetation ◽  
Sentinel 2

The electromagnetic spectrum registered via satellite remote sensing methods became a popular data source that can enrich traditional methods of vegetation monitoring. The European Space Agency Sentinel-2 mission, thanks to its spatial (10–20 m) and spectral resolution (12 spectral bands registered in visible-, near-, and mid-infrared spectrum) and primarily its short revisit time (5 days), helps to provide reliable and accurate material for the identification of mountain vegetation. Using the support vector machines (SVM) algorithm and reference data (botanical map of non-forest vegetation, field survey data, and high spatial resolution images) it was possible to classify eight vegetation types of Giant Mountains: bogs and fens, deciduous shrub vegetation, forests, grasslands, heathlands, subalpine tall forbs, subalpine dwarf pine scrubs, and rock and scree vegetation. Additional variables such as principal component analysis (PCA) bands and selected vegetation indices were included in the best classified dataset. The results of the iterative classification, repeated 100 times, were assessed as approximately 80% median overall accuracy (OA) based on multi-temporal datasets composed of images acquired through the vegetation growing season (from late spring to early autumn 2018), better than using a single-date scene (70%–72% OA). Additional variables did not significantly improve the results, showing the importance of spectral and temporal information themselves. Our study confirms the possibility of fully available data for the identification of mountain vegetation for management purposes and protection within national parks.

scholarly journals Integration of UAV, Sentinel-1 and Sentinel-2 Data for Mangrove Plantations Aboveground Biomass Monitoring in Senegal

2018 ◽  
Author(s):  
José Antonio Navarro ◽  
Nur Algeet ◽  
Alfredo Fernández-Landa ◽  
Jéssica Esteban ◽  
Pablo Rodríguez-Noriega ◽  
...  
Keyword(s):  
Aboveground Biomass ◽  
Auxiliary Information ◽  
Tree Height ◽  
Cost Effective ◽  
Point Clouds ◽  
Support Vector ◽  
Monitoring Methods ◽  
Individual Tree ◽  
Entire Study ◽  
Sentinel 2

Due to the increasing importance of mangroves in climate change mitigation projects, more accurate and cost-effective aboveground biomass (AGB) monitoring methods are required. However, field measurement of AGB may be a challenge because of its remote location and the difficulty to walk in these areas. This study is based on the Livelihoods Fund’ Oceanium project of 10,000 hectare mangrove plantations monitoring. In a first step, the possibility of replacing traditional field measurements of sample plots in a young mangrove plantation by a semiautomatic processing of UAV-based photogrammetric point clouds was assessed. In a second step, Sentinel-1 radar and Sentinel-2 optical imagery were used as auxiliary information to estimate AGB and its variance for the entire study area under a model-assisted framework. AGB was measured using UAV imagery in a total of 95 sample plots. UAV plot data was used in combination with non-parametric Support Vector Regression (SVR) models for the estimation of the study area AGB using model-assisted estimators. Purely UAV-based AGB estimates and their associated standard error (SE) were compared with model-assisted estimates using (1) Sentinel-1, (2) Sentinel-2 and (3) a combination of Sentinel-1 and Sentinel-2 data as auxiliary information. The validation of the UAV-based individual tree height and crown diameter measurements showed a root mean square error (RMSE) of 0.21 m and 0.32 m respectively. Relative efficiency of the three model-assisted scenarios ranged between 1.61 and 2.15. Although all SVR models improved the efficiency of the monitoring over UAV-based estimates, the best results were achieved when a combination of Sentinel-1 and Sentinel-2 data was used. Results indicated that the methodology used in this research can provide accurate and cost-effective estimates of AGB in mangrove young plantations.

scholarly journals An Improved Multi-temporal and Multi-feature Tea Plantation Identification Method Using Sentinel-2 Imagery

Sensors ◽  
2019 ◽  
Vol 19 (9) ◽  
pp. 2087 ◽  
Author(s):  
Jun Zhu ◽  
Ziwu Pan ◽  
Hang Wang ◽  
Peijie Huang ◽  
Jiulin Sun ◽  
...  
Keyword(s):  
Support Vector ◽  
Machine Method ◽  
Tea Plantation ◽  
Classification Feature ◽  
Feature Importance ◽  
Tea Plantations ◽  
Periodic Monitoring ◽  
Multi Temporal ◽  
Importance Analysis ◽  
Sentinel 2

As tea is an important economic crop in many regions, efficient and accurate methods for remotely identifying tea plantations are essential for the implementation of sustainable tea practices and for periodic monitoring. In this study, we developed and tested a method for tea plantation identification based on multi-temporal Sentinel-2 images and a multi-feature Random Forest (RF) algorithm. We used phenological patterns of tea cultivation in China’s Shihe District (such as the multiple annual growing, harvest, and pruning stages) to extracted multi-temporal Sentinel-2 MSI bands, their derived first spectral derivative, NDVI and textures, and topographic features. We then assessed feature importance using RF analysis; the optimal combination of features was used as the input variable for RF classification to extract tea plantations in the study area. A comparison of our results with those achieved using the Support Vector Machine method and statistical data from local government departments showed that our method had a higher producer’s accuracy (96.57%) and user’s accuracy (96.02%). These results demonstrate that: (1) multi-temporal and multi-feature classification can improve the accuracy of tea plantation recognition, (2) RF classification feature importance analysis can effectively reduce feature dimensions and improve classification efficiency, and (3) the combination of multi-temporal Sentinel-2 images and the RF algorithm improves our ability to identify and monitor tea plantations.

scholarly journals Improvement in Land Cover and Crop Classification based on Temporal Features Learning from Sentinel-2 Data Using Recurrent-Convolutional Neural Network (R-CNN)

2019 ◽  
Vol 10 (1) ◽  
pp. 238 ◽  
Author(s):  
Vittorio Mazzia ◽  
Aleem Khaliq ◽  
Marcello Chiaberge
Keyword(s):  
Neural Networks ◽  
Land Cover ◽  
Machine Learning Algorithms ◽  
Series Data ◽  
Support Vector ◽  
Agricultural Crops ◽  
Sensing Applications ◽  
Multi Temporal ◽  
Crop Classification ◽  
Sentinel 2

Understanding the use of current land cover, along with monitoring change over time, is vital for agronomists and agricultural agencies responsible for land management. The increasing spatial and temporal resolution of globally available satellite images, such as provided by Sentinel-2, creates new possibilities for researchers to use freely available multi-spectral optical images, with decametric spatial resolution and more frequent revisits for remote sensing applications such as land cover and crop classification (LC&CC), agricultural monitoring and management, environment monitoring. Existing solutions dedicated to cropland mapping can be categorized based on per-pixel based and object-based. However, it is still challenging when more classes of agricultural crops are considered at a massive scale. In this paper, a novel and optimal deep learning model for pixel-based LC&CC is developed and implemented based on Recurrent Neural Networks (RNN) in combination with Convolutional Neural Networks (CNN) using multi-temporal sentinel-2 imagery of central north part of Italy, which has diverse agricultural system dominated by economic crop types. The proposed methodology is capable of automated feature extraction by learning time correlation of multiple images, which reduces manual feature engineering and modeling crop phenological stages. Fifteen classes, including major agricultural crops, were considered in this study. We also tested other widely used traditional machine learning algorithms for comparison such as support vector machine SVM, random forest (RF), Kernal SVM, and gradient boosting machine, also called XGBoost. The overall accuracy achieved by our proposed Pixel R-CNN was 96.5%, which showed considerable improvements in comparison with existing mainstream methods. This study showed that Pixel R-CNN based model offers a highly accurate way to assess and employ time-series data for multi-temporal classification tasks.

scholarly journals Land Use/Land Cover Mapping Using Multitemporal Sentinel-2 Imagery and Four Classification Methods—A Case Study from Dak Nong, Vietnam

2020 ◽  
Vol 12 (9) ◽  
pp. 1367 ◽  
Author(s):  
Huong Thi Thanh Nguyen ◽  
Trung Minh Doan ◽  
Erkki Tomppo ◽  
Ronald E. McRoberts
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Forest Cover ◽  
Confusion Matrix ◽  
Support Vector ◽  
Remotely Sensed Data ◽  
K Nearest Neighbors ◽  
Tropical Regions ◽  
Multi Temporal ◽  
Sentinel 2

Information on land use and land cover (LULC) including forest cover is important for the development of strategies for land planning and management. Satellite remotely sensed data of varying resolutions have been an unmatched source of such information that can be used to produce estimates with a greater degree of confidence than traditional inventory estimates. However, use of these data has always been a challenge in tropical regions owing to the complexity of the biophysical environment, clouds, and haze, and atmospheric moisture content, all of which impede accurate LULC classification. We tested a parametric classifier (logistic regression) and three non-parametric machine learning classifiers (improved k-nearest neighbors, random forests, and support vector machine) for classification of multi-temporal Sentinel 2 satellite imagery into LULC categories in Dak Nong province, Vietnam. A total of 446 images, 235 from the year 2017 and 211 from the year 2018, were pre-processed to gain high quality images for mapping LULC in the 6516 km2 study area. The Sentinel 2 images were tested and classified separately for four temporal periods: (i) dry season, (ii) rainy season, (iii) the entirety of the year 2017, and (iv) the combination of dry and rainy seasons. Eleven different LULC classes were discriminated of which five were forest classes. For each combination of temporal image set and classifier, a confusion matrix was constructed using independent reference data and pixel classifications, and the area on the ground of each class was estimated. For overall temporal periods and classifiers, overall accuracy ranged from 63.9% to 80.3%, and the Kappa coefficient ranged from 0.611 to 0.813. Area estimates for individual classes ranged from 70 km2 (1% of the study area) to 2200 km2 (34% of the study area) with greater uncertainties for smaller classes.

Automatic glacier outlines extraction from Sentinel-1 and Sentinel-2 time series

2020 ◽  
Author(s):  
Riccardo Barella ◽  
Mattia Callegari ◽  
Carlo Marin ◽  
Claudia Notarnicola ◽  
Marc Zebisch ◽  
...  
Keyword(s):  
Time Series ◽  
Snow Cover ◽  
Short Wave ◽  
Support Vector ◽  
Glacier Inventory ◽  
Multi Temporal ◽  
Manual Selection ◽  
The Alps ◽  
Loss Of Coherence ◽  
Sentinel 2

<p>Glaciers represent an important part of the hydrologic cycle in the Alps and they are very sensitive to climate change. Satellite remote sensing is an efficient tool for glacier monitoring because it provides a synoptic view over large areas. In literature, well-established methods for glacier delineation based on the Red and Short Wave Infrared (SWIR) ratio have been presented. These methods depend on a manual selection for each glacier of the “best scene”, i.e. absence of cloud coverage and minimum snow cover. A further manual refinement step is needed to handle possible errors, mainly due to cloud cover or shadows, and to include debris covered ice.</p><p>A manual approach for glacier outline extraction, especially if applied over large areas and beside the respective extraordinary amount of work, may be inadequate for at least two reasons:</p><p>1) The increased amount of available satellite data provided by the recently launched Sentinel-2 mission, which ensure at least one acquisition every 5 days on a given area;</p><p>2) The need for a more frequent update of the glacier outlines i.e. few years, due to the faster changes affecting glaciers during the last years.</p><p>In this work, we present an automatic method for glacier mapping, including bare ice and debris covered ice through the synergetic use of Sentinel-1 and Sentinel-2. The information of the Sentinel-2 time series is first classified with a Support Vector Machine (SVM) to detect cloud and snow. The snow and cloud masks are then used to select the non-cloudy pixels with the lowest snow coverage in the surrounding area. This is done by applying a moving window on the entire multi-temporal classified stack. The selected pixels for each band compose a multi-temporal cloud free mosaic, which represents the glaciers with the minimum snow cover for the current ablation season i.e., the “best scene”. If we compose the mosaic with classified pixels instead of the reflectance, we obtain the glacier – non glacier map that we use for outlines extraction. On the other hand, the Sentinel-1 coherence is used to detect the debris-covered ice over the areas classified as non-glacier from Sentinel-2. In detail, the Sentinel-1 time series is exploited to generate a multi-temporal coherence mosaic, which is representative of the loss of coherence due to the movement of the debris only. By properly thresholding this mosaic and considering the topographic information, the outlines of debris covered glaciers can be extracted.</p><p>The results obtained with the proposed method are compared with the recent official glacier inventory of South Tyrol (Italy) and Tyrol (Austria), which was derived from the manual interpretation of aerial orthophotos and lidar data by glacier experts.</p>

Sign in / Sign up

Export Citation Format

Share Document