scholarly journals Economic losses caused by tree species proportions and site type errors in forest management planning

Silva Fennica ◽  
2019 ◽  
Vol 53 (2) ◽  
Author(s):  
Arto Haara ◽  
Annika Kangas ◽  
Sakari Tuominen
Keyword(s):  
Satellite Data ◽  
Tree Species ◽  
Forest Inventory ◽  
Ground Truth ◽  
Study Data ◽  
Aerial Image ◽  
Economic Losses ◽  
Ground Truth Data ◽  
Site Type ◽  
Species Proportions

The aim of this study was to estimate economic losses, which are caused by forest inventory errors of tree species proportions and site types. Our study data consisted of ground truth data and four sets of erroneous tree species proportions. They reflect the accuracy of tree species proportions in four remote sensing data sets, namely 1) airborne laser scanning (ALS) with 2D aerial image, 2) 2D aerial image, 3) 3D and 2D aerial image data together and 4) satellite data. Furthermore, our study data consisted of one simulated site type data set. We used the erroneous tree species proportions to optimise the timing of forest harvests and compared that to the true optimum obtained with ground truth data. According to the results, the mean losses of Net Present Value (NPV) because of erroneous tree species proportions at an interest rate of 3% varied from 124.4 € ha to 167.7 € ha. The smallest losses were observed using tree species proportions predicted using ALS data and largest using satellite data. In those stands, respectively, in which tree species proportion errors actually caused economic losses, they were 468 € ha on average with tree species proportions based on ALS data. In turn, site type errors caused only small losses. Based on this study, accurate tree species identification seems to be very important with respect to operational forest inventory.–1–1–1

scholarly journals EXPLORING MACHINE LEARNING CLASSIFICATION ALGORITHMS FOR CROP CLASSIFICATION USING SENTINEL 2 DATA

2019 ◽  
Vol XLII-3/W6 ◽  
pp. 573-578 ◽  
Author(s):  
◽  
S. S. Ray
Keyword(s):  
Machine Learning ◽  
Satellite Data ◽  
Classification Accuracy ◽  
Ground Truth ◽  
Kappa Coefficient ◽  
Ground Truth Data ◽  
Classification Techniques ◽  
Machine Learning Classification ◽  
Crop Classification ◽  
Sentinel 2

<p><strong>Abstract.</strong> Crop Classification and recognition is a very important application of Remote Sensing. In the last few years, Machine learning classification techniques have been emerging for crop classification. Google Earth Engine (GEE) is a platform to explore the multiple satellite data with different advanced classification techniques without even downloading the satellite data. The main objective of this study is to explore the ability of different machine learning classification techniques like, Random Forest (RF), Classification And Regression Trees (CART) and Support Vector Machine (SVM) for crop classification. High Resolution optical data, Sentinel-2, MSI (10&amp;thinsp;m) was used for crop classification in the Indian Agricultural Research Institute (IARI) farm for the Rabi season 2016 for major crops. Around 100 crop fields (~400 Hectare) in IARI were analysed. Smart phone-based ground truth data were collected. The best cloud free image of Sentinel 2 MSI data (5 Feb 2016) was used for classification using automatic filtering by percentage cloud cover property using the GEE. Polygons as feature space was used as training data sets based on the ground truth data for crop classification using machine learning techniques. Post classification, accuracy assessment analysis was done through the generation of the confusion matrix (producer and user accuracy), kappa coefficient and F value. In this study it was found that using GEE through cloud platform, satellite data accessing, filtering and pre-processing of satellite data could be done very efficiently. In terms of overall classification accuracy and kappa coefficient, Random Forest (93.3%, 0.9178) and CART (73.4%, 0.6755) classifiers performed better than SVM (74.3%, 0.6867) classifier. For validation, Field Operation Service Unit (FOSU) division of IARI, data was used and encouraging results were obtained.</p>

scholarly journals Potentiality and Limitations of Open Satellite Data for Flood Mapping

2018 ◽  
Author(s):  
Davide Notti ◽  
Daniele Giordan ◽  
Fabiana Calò ◽  
Antonio Pepe ◽  
Francesco Zucca ◽  
...  
Keyword(s):  
Satellite Data ◽  
Low Cost ◽  
Ground Truth ◽  
Flood Mapping ◽  
Ancillary Data ◽  
Ground Truth Data ◽  
Flood Peak ◽  
Sar Data ◽  
Flooded Areas ◽  
Flood Maps

Satellite remote sensing is a powerful tool to map flooded areas. In the last years, the availability of free satellite data sensibly increased in terms of type and frequency, allowing producing flood maps at low cost around the World. In this work, we propose a semi-automatic method for flood mapping, based only on free satellite images and open-source software. As case studies, we selected three flood events recently occurred in Spain and Italy. Multispectral satellite data acquired by MODIS, Proba-V, Landsat, Sentinel-2 and SAR data collected by Sentinel-1 were used to detect flooded areas using different methodologies (e.g., MNDWI; SAR backscattering variation; Supervised classification). Then, we improved and manually refined the automatic mapping using free ancillary data like DEM based water depth model and available ground truth data. For the areas affected by major floods, we also validated and compared the produced flood maps with official maps made by river authorities. We calculated flood detection performance (flood ratio) for the different datasets we used. The results show that it is necessary to take into account different factors for the choice of best satellite data, among these, the time of satellite pass with respect to the flood peak is the most important one. SAR data showed good results only for co-flood acquisitions, whereas multispectral images allowed detecting flooded areas also with the post-flood acquisition. With the support of ancillary data, it was possible to produce reliable geomorphological based flood maps in the study areas.

Characterization of Alpine peatlands based on remote sensing of vegetation and water content

2021 ◽  
Author(s):  
Sonia Silvestri ◽  
Alessandra Borgia
Keyword(s):  
Remote Sensing ◽  
Water Content ◽  
Spatial Resolution ◽  
Satellite Data ◽  
Regional Scale ◽  
Ground Truth ◽  
Organic Carbon Content ◽  
Ground Truth Data ◽  
The World ◽  
The Eu

&lt;p&gt;Storing up to 70 kg of carbon per cubic meter, peatlands are among the most carbon-dense environments in the world. If in pristine conditions, peatlands support a number of ecosystem services as for example water retention and mitigation of droughts and floods, water purification, water availability to wildlife. Their preservation is one of the main goals of the EU policy and of other initiatives around the world.&lt;/p&gt;&lt;p&gt;Despite their importance, Alpine peatlands have been rarely studied and their presence is not even included in the EU maps, as for example the JRC Relative Cover of Peat Soils map, and only some sites are included in the Corine Land Cover map. The precise localization of peatland sites and the assessment of their extent is the first fundamental step for the implementation of adequate conservation policies. To this end, satellite remote sensing is the ideal instrument to provide adequate spatial resolution to detect and characterize Alpine peatlands at the regional scale. In this study, we use Sentinal-2 satellite data combined with 2m spatial resolution digital elevation model (from LiDAR data) to detect and quantify the extent of peatlands in the Trentino - Alto Adige region, an area of about 12,000 sq km located in the heart of the Italian Alpine region. Ground truth data include 71 peatlands that cover a total surface of more than 2,000 sq m. Field campaigns and lab analyses on some selected sites show that, on average, the sampled peatlands have depth of about 1m, Bulk Density of 0.128 g cm&lt;sup&gt;-3&lt;/sup&gt; and LOI of 63%, hence indicating that the organic carbon content by soil volume is high, being on average 0.04 g cm&lt;sup&gt;-3&lt;/sup&gt;. Satellite data analysis allowed us to detect a large number of peatland sites with high accuracy, thus confirming the importance of Alpine peatlands as carbon stock sites for the region. Moreover, thanks to the correlation between two indices (NDVI and NDWI) we could characterize the water content of these sites, hence analyzing its seasonal variation and inferring possible future scenarios linked to climate change effects.&lt;/p&gt;

Calculating macroalgal height and biomass using bathymetric LiDAR and a comparison with surface area derived from satellite data in Nova Scotia, Canada

2020 ◽  
Vol 63 (1) ◽  
pp. 43-59 ◽  
Author(s):  
Tim Webster ◽  
Candace MacDonald ◽  
Kevin McGuigan ◽  
Nathan Crowell ◽  
Jean-Sebastien Lauzon-Guay ◽  
...  
Keyword(s):  
Nova Scotia ◽  
Surface Area ◽  
Survey Data ◽  
Satellite Data ◽  
High Tide ◽  
Field Measurements ◽  
Ground Truth ◽  
Cost Effective ◽  
Satellite System ◽  
Ground Truth Data

AbstractThe ability to map and monitor the macroalgal coastal resource is important to both the industry and the regulator. This study evaluates topo-bathymetric lidar (light detection and ranging) as a tool for estimating the surface area, height and biomass of Ascophyllum nodosum, an anchored and vertically suspended (floating) macroalga, and compares the surface area derived from lidar and WorldView-2 satellite imagery. Pixel-based Maximum Likelihood classification of low tide satellite data produced 2-dimensional maps of intertidal macroalgae with overall accuracy greater than 80%. Low tide and high tide topo-bathymetric lidar surveys were completed in southwestern Nova Scotia, Canada. Comparison of lidar-derived seabed elevations with ground-truth data collected using a survey grade global navigation satellite system (GNSS) indicated the low tide survey data have a positive bias of 15 cm, likely resulting from the seaweed being draped over the surface. The high tide survey data did not exhibit this bias, although the suspended canopy floating on the water surface reduced the seabed lidar point density. Validation of lidar-derived seaweed heights indicated a mean difference of 30 cm with a root mean square error of 62 cm. The modelled surface area of seaweed was 28% greater in the lidar model than the satellite model. The average lidar-derived biomass estimate was within one standard deviation of the mean biomass measured in the field. The lidar method tends to overestimate the biomass compared to field measurements that were spatially biased to the mid-intertidal level. This study demonstrates an innovative and cost-effective approach that uses a single high tide bathymetric lidar survey to map the height and biomass of dense macroalgae.

scholarly journals Classification of trees and the effects of thinning in the artificially established spruce stand in the area of Sokolina-Kotor Varos

2007 ◽  
pp. 29-43
Author(s):  
Zoran Govedar
Keyword(s):  
Adverse Effects ◽  
Tree Species ◽  
Forest Inventory ◽  
Economic Losses ◽  
Stem Quality ◽  
The Republic ◽  
Tree Quality ◽  
Forestry Practice

The classifications of trees are mainly based on descriptive (attributive) characters and they have a great significance in thinning. In forestry practice (tree marking for felling, forest inventory, etc) in the Republic of Srpska, the most frequently applied classifications are silvicultural-technical (UT) and technical classification of trees, which are based on the knowledge of tree species, stem diameter and stem quality. In IUFRO classification, based on the silvicultural role of trees, and in UT classification, the trees are classified in three categories. The knowledge and application of these classifications is especially significant in the management of artificially established stands. Economic losses in spruce plantations occur because of untimely tending, especially thinning, which has multiple adverse effects on tree quality. The aim of this paper is to point out the application and the relation of UT and IUFRO classifications, as well as the effect of thinning on tree quality structure in both classifications. The research was performed in a 29-years-old spruce plantation established in the belt of mixed forests of beech and fir. The silvicultural-technical and IUFRO classifications were performed and compared in the aim of their application in different thinning treatments (high thinning of light and moderate weight and mixed thinning of moderate weight). Taking into account the state of spruce plantations in the Republic of Srpska, the effect of thinning on stand quality structure was researched and UT classification of trees applied in practice was compared with IUFRO classification.

scholarly journals ANALYSIS OF WHEAT CROP FORECASTS, IN INDIA, GENERATED USING REMOTE SENSING DATA, UNDER FASAL PROJECT

2019 ◽  
Vol XLII-3/W6 ◽  
pp. 223-228
Author(s):  
S. Kumar ◽  
S. Saxena ◽  
S. K. Dubey ◽  
K. Chaudhary ◽  
S. Sehgal ◽  
...  
Keyword(s):  
Correlation Coefficient ◽  
Spatial Resolution ◽  
Satellite Data ◽  
National Level ◽  
Remote Sensing Data ◽  
State Level ◽  
Ground Truth ◽  
District Level ◽  
Wheat Crop ◽  
Ground Truth Data

<p><strong>Abstract.</strong> Wheat (<i>Triticum aestivum</i> L.) is a major cereal crop of the world, which plays an important role in global food and nutritional security. In India, wheat grown areas are more as compared to other food crops, except for rice. The total area under wheat cultivation is 30.60 million hectares with production of 98.38 million tonnes and the productivity is 3.22 tonnes /hectare (DES, 2017). The main objective of this paper is to highlight the development of satellite-based methodology, compare the relative deviations (%) at national level, RMSE (%) and correlation coefficient at state level and correlation coefficient at district level between DES and FASAL estimates from 2013 to 2017. It was observed that the area and production estimates improved with improvement in the satellite resolution and ground truth data. During the last 10 years of estimation the spatial resolution of the satellite data has gradually improved from 23.5 meter of (Reourcesat-2, LISS-III) and finally 10&amp;thinsp;m of Sentinel-2, MSI, which is being currently used for acreage estimation purpose. Hooda R.S et al (2006) studied that the improvement in the spatial resolution, spectral and temporal resolution of the satellite data has also improved the crop discrimination. Both accuracy as well as precision of the estimates has improved over the years from 2013 to 2017, as reflected by relative deviation, RMSE (%) and Coefficient of correlation values at national, state and district level respectively.</p>

scholarly journals Comparing UAV-Based Technologies and RGB-D Reconstruction Methods for Plant Height and Biomass Monitoring on Grass Ley

Sensors ◽  
2019 ◽  
Vol 19 (3) ◽  
pp. 535 ◽  
Author(s):  
Victor Rueda-Ayala ◽  
José Peña ◽  
Mats Höglind ◽  
José Bengochea-Guevara ◽  
Dionisio Andújar
Keyword(s):  
Plant Height ◽  
Ground Truth ◽  
Aerial Image ◽  
Ground Truth Data ◽  
Reconstruction Methods ◽  
Digital Modeling ◽  
Data Resolution ◽  
Dry Biomass ◽  
Aerial Platforms ◽  
Grass Ley

Pastures are botanically diverse and difficult to characterize. Digital modeling of pasture biomass and quality by non-destructive methods can provide highly valuable support for decision-making. This study aimed to evaluate aerial and on-ground methods to characterize grass ley fields, estimating plant height, biomass and volume, using digital grass models. Two fields were sampled, one timothy-dominant and the other ryegrass-dominant. Both sensing systems allowed estimation of biomass, volume and plant height, which were compared with ground truth, also taking into consideration basic economical aspects. To obtain ground-truth data for validation, 10 plots of 1 m2 were manually and destructively sampled on each field. The studied systems differed in data resolution, thus in estimation capability. There was a reasonably good agreement between the UAV-based, the RGB-D-based estimates and the manual height measurements on both fields. RGB-D-based estimation correlated well with ground truth of plant height ( R 2 > 0.80 ) for both fields, and with dry biomass ( R 2 = 0.88 ), only for the timothy field. RGB-D-based estimation of plant volume for ryegrass showed a high agreement ( R 2 = 0.87 ). The UAV-based system showed a weaker estimation capability for plant height and dry biomass ( R 2 < 0.6 ). UAV-systems are more affordable, easier to operate and can cover a larger surface. On-ground techniques with RGB-D cameras can produce highly detailed models, but with more variable results than UAV-based models. On-ground RGB-D data can be effectively analysed with open source software, which is a cost reduction advantage, compared with aerial image analysis. Since the resolution for agricultural operations does not need fine identification the end-details of the grass plants, the use of aerial platforms could result a better option in grasslands.

Contribution to the automation of the calculations involving the forest inventory with the aid of an office computer

1970 ◽  
Vol 20 ◽  
Author(s):  
R. Goossens
Keyword(s):  
Tree Species ◽  
Forest Inventory ◽  
Basal Area ◽  
Annual Increment ◽  
Mixed Stands ◽  
Mean Values ◽  
Standing Trees ◽  
General Program ◽  
Magnetic Card ◽  
The Right

Contribution to the automation of the calculations involving  the forest inventory with the aid of an office computer - In this contribution an attempt was made to perform the  calculations involving the forest inventory by means of an office computer  Olivetti P203.     The general program (flowchart 1), identical for all tree species except  for the values of the different parameters, occupies the tracks A and B of a  magnetic card used with this computer. For each tree species one magnetic  card is required, while some supplementary cards are used for the  subroutines. The first subroutine (flowchart 1) enables us to preserve  temporarily the subtotals between two tree species (mixed stands) and so  called special or stand cards (SC). After the last tree species the totals  per ha are calculated and printed on the former, the average trees occuring  on the line below. Appendix 1 gives an example of a similar form resulting  from calculations involving a sampling in a mixed stand consisting of Oak  (code 11), Red oak (code 12), Japanese larch (code 24) and Beech (code 13).  On this form we find from the left to the right: the diameter class (m), the  number of trees per ha, the basal area (m2/ha), the current annual increment  of the basal area (m2/year/ha), current annual volume increment (m3/year/ha),  the volume (m3/ha) and the money value of the standing trees (Bfr/ha). On the  line before the last, the totals of the quantities mentioned above and of all  the tree species together are to be found. The last line gives a survey of  the average values dg, g, ig, ig, v and w.     Besides this form each stand or plot has a so-called 'stand card SC' on  wich the totals cited above as well as the area of the stand or the plot and  its code are stored. Similar 'stand card' may replace in many cases  completely the classical index cards; moreover they have the advantage that  the data can be entered directly into the computer so that further  calculations, classifications or tabling can be carried out by means of an  appropriate program or subroutine. The subroutine 2 (flowchart 2) illustrates  the use of similar cards for a series of stands or eventually a complete  forest, the real values of the different quantities above are calculated and  tabled (taking into account the area). At the same time the general totals  and the general mean values per ha, as well as the average trees are  calculated and printed. Appendix 2 represents a form resulting from such  calculations by means of subroutine 2.

scholarly journals Fig Plant Segmentation from Aerial Images Using a Deep Convolutional Encoder-Decoder Network

2019 ◽  
Vol 11 (10) ◽  
pp. 1157 ◽  
Author(s):  
Jorge Fuentes-Pacheco ◽  
Juan Torres-Olivares ◽  
Edgar Roman-Rangel ◽  
Salvador Cervantes ◽  
Porfirio Juarez-Lopez ◽  
...  
Keyword(s):  
Precision Agriculture ◽  
Image Data ◽  
Ground Truth ◽  
Aerial Images ◽  
Aerial Image ◽  
Data Set ◽  
Visual Appearance ◽  
Aerial Robots ◽  
Lighting Conditions ◽  
Convolutional Encoder

Crop segmentation is an important task in Precision Agriculture, where the use of aerial robots with an on-board camera has contributed to the development of new solution alternatives. We address the problem of fig plant segmentation in top-view RGB (Red-Green-Blue) images of a crop grown under open-field difficult circumstances of complex lighting conditions and non-ideal crop maintenance practices defined by local farmers. We present a Convolutional Neural Network (CNN) with an encoder-decoder architecture that classifies each pixel as crop or non-crop using only raw colour images as input. Our approach achieves a mean accuracy of 93.85% despite the complexity of the background and a highly variable visual appearance of the leaves. We make available our CNN code to the research community, as well as the aerial image data set and a hand-made ground truth segmentation with pixel precision to facilitate the comparison among different algorithms.

scholarly journals Assessing Wildfire Burn Severity and Its Relationship with Environmental Factors: A Case Study in Interior Alaska Boreal Forest

2021 ◽  
Vol 13 (10) ◽  
pp. 1966
Author(s):  
Christopher W Smith ◽  
Santosh K Panda ◽  
Uma S Bhatt ◽  
Franz J Meyer ◽  
Anushree Badola ◽  
...  
Keyword(s):  
Boreal Forest ◽  
Ground Truth ◽  
Burn Severity ◽  
Classification Methods ◽  
Spectral Indices ◽  
Ground Truth Data ◽  
Burn Scar ◽  
Interior Alaska ◽  
Remote Sensing Methods ◽  
The Relationship

In recent years, there have been rapid improvements in both remote sensing methods and satellite image availability that have the potential to massively improve burn severity assessments of the Alaskan boreal forest. In this study, we utilized recent pre- and post-fire Sentinel-2 satellite imagery of the 2019 Nugget Creek and Shovel Creek burn scars located in Interior Alaska to both assess burn severity across the burn scars and test the effectiveness of several remote sensing methods for generating accurate map products: Normalized Difference Vegetation Index (NDVI), Normalized Burn Ratio (NBR), and Random Forest (RF) and Support Vector Machine (SVM) supervised classification. We used 52 Composite Burn Index (CBI) plots from the Shovel Creek burn scar and 28 from the Nugget Creek burn scar for training classifiers and product validation. For the Shovel Creek burn scar, the RF and SVM machine learning (ML) classification methods outperformed the traditional spectral indices that use linear regression to separate burn severity classes (RF and SVM accuracy, 83.33%, versus NBR accuracy, 73.08%). However, for the Nugget Creek burn scar, the NDVI product (accuracy: 96%) outperformed the other indices and ML classifiers. In this study, we demonstrated that when sufficient ground truth data is available, the ML classifiers can be very effective for reliable mapping of burn severity in the Alaskan boreal forest. Since the performance of ML classifiers are dependent on the quantity of ground truth data, when sufficient ground truth data is available, the ML classification methods would be better at assessing burn severity, whereas with limited ground truth data the traditional spectral indices would be better suited. We also looked at the relationship between burn severity, fuel type, and topography (aspect and slope) and found that the relationship is site-dependent.

Sign in / Sign up

Export Citation Format

Share Document