scholarly journals The Return of Nature to the Chernobyl Exclusion Zone: Increases in Forest Cover of 1.5 Times since the 1986 Disaster

Forests ◽  
2021 ◽  
Vol 12 (8) ◽  
pp. 1024
Author(s):  
Maksym Matsala ◽  
Andrii Bilous ◽  
Viktor Myroniuk ◽  
Dmytrii Holiaka ◽  
Dmitry Schepaschenko ◽  
...  
Keyword(s):  
Land Cover ◽  
Management Practices ◽  
Forest Cover ◽  
Natural Disturbance ◽  
Training Data ◽  
Classification Model ◽  
Ecosystem Functions ◽  
Exclusion Zone ◽  
Temporal Segmentation ◽  
Random Forest Classification

For 34 years since the 1986 nuclear disaster, the Chernobyl Exclusion Zone (ChEZ) landscapes have been protected with very limited human interventions. Natural afforestation has largely occurred throughout the abandoned farmlands, while natural disturbance regimes, which dominantly include wildfires, have become more frequent and severe in the last years. Here, we utilize the dense time series of Landsat satellite imagery (1986–2020) processed by using the temporal segmentation algorithm LandTrendr in order to derive a robust land cover and forest mask product for the ChEZ. Additionally, we carried out an analysis of land cover transitions on the former farmlands. The Random Forest classification model developed here has achieved overall accuracies of 80% (using training data for 2017) and 89% on a binary “forest/non-forest” validation (using data from 1988). The total forest cover area within the ChEZ has increased from 41% (in 1986) to 59% (in 2020). This forest gain can be explained by the afforestation that has occurred in abandoned farmlands, which compensates for forest cover losses due to large fire events in 1992, 2015–2016, and 2020. Most transitions from open landscapes to dense forest cover occurred after the year 2000 and are possibly linked to past forest management practices. We conclude that a consistent forest strategy, with the aid of remote monitoring, is required to efficiently manage new forests in the ChEZ in order to retain their ecosystem functions and to ensure sustainable habitats.

scholarly journals Continental-Scale Land Cover Mapping at 10 m Resolution Over Europe (ELC10)

2021 ◽  
Vol 13 (12) ◽  
pp. 2301
Author(s):  
Zander Venter ◽  
Markus Sydenham
Keyword(s):  
Land Cover ◽  
Atmospheric Correction ◽  
Google Earth ◽  
Tree Planting ◽  
Training Data ◽  
Classification Model ◽  
Night Time ◽  
Continental Scale ◽  
Land Cover Maps ◽  
Sentinel 2

Land cover maps are important tools for quantifying the human footprint on the environment and facilitate reporting and accounting to international agreements addressing the Sustainable Development Goals. Widely used European land cover maps such as CORINE (Coordination of Information on the Environment) are produced at medium spatial resolutions (100 m) and rely on diverse data with complex workflows requiring significant institutional capacity. We present a 10 m resolution land cover map (ELC10) of Europe based on a satellite-driven machine learning workflow that is annually updatable. A random forest classification model was trained on 70K ground-truth points from the LUCAS (Land Use/Cover Area Frame Survey) dataset. Within the Google Earth Engine cloud computing environment, the ELC10 map can be generated from approx. 700 TB of Sentinel imagery within approx. 4 days from a single research user account. The map achieved an overall accuracy of 90% across eight land cover classes and could account for statistical unit land cover proportions within 3.9% (R2 = 0.83) of the actual value. These accuracies are higher than that of CORINE (100 m) and other 10 m land cover maps including S2GLC and FROM-GLC10. Spectro-temporal metrics that capture the phenology of land cover classes were most important in producing high mapping accuracies. We found that the atmospheric correction of Sentinel-2 and the speckle filtering of Sentinel-1 imagery had a minimal effect on enhancing the classification accuracy (< 1%). However, combining optical and radar imagery increased accuracy by 3% compared to Sentinel-2 alone and by 10% compared to Sentinel-1 alone. The addition of auxiliary data (terrain, climate and night-time lights) increased accuracy by an additional 2%. By using the centroid pixels from the LUCAS Copernicus module polygons we increased accuracy by <1%, revealing that random forests are robust against contaminated training data. Furthermore, the model requires very little training data to achieve moderate accuracies—the difference between 5K and 50K LUCAS points is only 3% (86 vs. 89%). This implies that significantly less resources are necessary for making in situ survey data (such as LUCAS) suitable for satellite-based land cover classification. At 10 m resolution, the ELC10 map can distinguish detailed landscape features like hedgerows and gardens, and therefore holds potential for aerial statistics at the city borough level and monitoring property-level environmental interventions (e.g., tree planting). Due to the reliance on purely satellite-based input data, the ELC10 map can be continuously updated independent of any country-specific geographic datasets.

Scenarios of the Tropical Dry Forest of Purulia District West Bengal

2020 ◽  
pp. 254-267
Author(s):  
Masuma Begum ◽  
Niloy Pramanick ◽  
Anirban Mukhopadhyay ◽  
Sayani Datta Majumdar
Keyword(s):  
Land Cover ◽  
Forest Cover ◽  
Vegetation Indices ◽  
Atmospheric Correction ◽  
Tropical Dry Forest ◽  
Dry Forest ◽  
Training Data ◽  
Change Dynamics ◽  
Land Cover Map ◽  
Purulia District

In this chapter, satellite images of the years 1995, 2005, and 2015 of LANDSAT have been used. After pre-processing (geometric correction and atmospheric correction using FLAASH, LULC change dynamics have been assessed to estimate the changes in total forest cover in Purulia district through an unsupervised K-means classification scheme. To evaluate the health status, vegetation indices, namely NDVI, SAVI, and CVI, have been used. The increase in NDVI, SAVI, and CVI values was inferred as no significant degradation of Purulia forest cover. Moreover, future scenarios have been predicted by implementing a CA-MARKOV model. Using the land cover map of 1995 as the base map, and from 1995 to 2005 as training data, a land cover map of 2015 has been generated which in turn validated by the actual land cover of 2015. After validation, prediction of land cover was possible for the years 2035 and 2050. The prediction suggested that forest area will increase by approximately 4% from 2015 to 2035 and by 3% from 2035 to 2050.

Joint production of timber, carbon, and wildlife habitat in the Canadian boreal plains

2008 ◽  
Vol 38 (6) ◽  
pp. 1478-1492 ◽  
Author(s):  
Geoffrey R. McCarney ◽  
Glen W. Armstrong ◽  
Wiktor L. Adamowicz
Keyword(s):  
Carbon Budget ◽  
Management Practices ◽  
Forest Cover ◽  
Natural Disturbance ◽  
Wildlife Habitat ◽  
Joint Production ◽  
Timber Supply ◽  
Budget Model ◽  
Carbon Budget Model ◽  
Trade Offs

This study investigates the relationships and trade-offs between forest carbon management, sustained timber yield, and the production of wildlife habitat to provide a more complete picture of the costs and challenges faced by forest managers for a particular case study in Canada’s boreal mixedwood region. The work presented is an extension of a previously published model that analysed the joint production of timber supply and wildlife habitat using a natural disturbance model approach to ecosystem management. The primary contribution of the present study is the detailed incorporation of a carbon budget model into the framework developed previously. Using the Carbon Budget Model of the Canadian Forest Sector, dynamics specific to separate biomass and dead organic matter carbon pools are represented for individual forest cover types. Results indicate the potential for cost thresholds in the joint production of timber supply and carbon sequestration. These thresholds are linked to switch points in the decision between multiple use and specialized land management practices. Cobenefits in the production of carbon and wildlife habitat are shown to depend on ecological parameters, harvest flow regulations, and incentives for timber supply provided by the market.

scholarly journals Stretching the Habitat Envelope: Insectivorous Bat Guilds Can Use Rubber Plantations, but Need Understorey Vegetation and Forest Buffers

2021 ◽  
Vol 2 ◽  
Author(s):  
Kadambari Deshpande ◽  
Nachiket Kelkar ◽  
Jagdish Krishnaswamy ◽  
Mahesh Sankaran
Keyword(s):  
Land Cover ◽  
Management Practices ◽  
Forest Cover ◽  
Foraging Strategies ◽  
Insectivorous Bats ◽  
Understorey Vegetation ◽  
Land Cover Types ◽  
Rubber Plantations ◽  
Bat Activity ◽  
Western Ghats Of India

Effects of land-cover change on insectivorous bat activity can be negative, neutral or positive, depending on foraging strategies of bats. In tropical agroforestry systems with high bat diversity, these effects can be complex to assess. We investigated foraging habitat use by three insectivorous bat guilds in forests and rubber plantations in the southern Western Ghats of India. Specifically, we monitored acoustic activity of bats in relation to (1) land-cover types and vegetation structure, and (2) plantation management practices. We hypothesized that activity of open-space aerial (OSA) and edge-space aerial (ESA) bat guilds would not differ; but narrow-space, flutter-detecting (NSFD) bat guild activity would be higher, in structurally heterogeneous forest habitats than monoculture rubber plantations. We found that bat activity of all guilds was highest in areas with high forest cover and lowest in rubber plantations. Higher bat activity was associated with understorey vegetation in forests and plantations, which was expected for NSFD bats, but was a surprise finding for OSA and ESA bats. Within land-cover types, open areas and edge-habitats had higher OSA and ESA activity respectively, while NSFD bats completely avoided open habitats. In terms of management practices, intensively managed rubber plantations with regular removal of understorey vegetation had the lowest bat activity for all guilds. Intensive management can undermine potential ecosystem services of insectivorous bats (e.g., insect pest-control in rubber plantations and surrounding agro-ecosystems), and magnify threats to bats from human disturbances. Low-intensity management and maintenance of forest buffers around plantations can enable persistence of insectivorous bats in tropical forest-plantation landscapes.

Reach-scale effects of riparian forest cover on urban stream ecosystems

2005 ◽  
Vol 62 (10) ◽  
pp. 2312-2329 ◽  
Author(s):  
Allison H Roy ◽  
Christina L Faust ◽  
Mary C Freeman ◽  
Judith L Meyer
Keyword(s):  
Land Cover ◽  
Management Practices ◽  
Forest Cover ◽  
Scale Effects ◽  
Riparian Forest ◽  
Canopy Cover ◽  
Habitat Diversity ◽  
Urban Stream ◽  
Ecosystem Integrity ◽  
Small Streams

We compared habitat and biota between paired open and forested reaches within five small streams (basin area 10–20 km2) in suburban catchments (9%–49% urban land cover) in the Piedmont of Georgia, USA. Stream reaches with open canopies were narrower than forested reaches (4.1 versus 5.0 m, respectively). There were no differences in habitat diversity (variation in velocity, depth, or bed particle size) between open and forested reaches. However, absence of local forest cover corresponded to decreased large wood and increased algal chlorophyll a standing crop biomass. These differences in basal food resources translated into higher densities of fishes in open (9.0 individuals·m–2) versus forested (4.9 individuals·m–2) reaches, primarily attributed to higher densities of the herbivore Campostoma oligolepis. Densities of terrestrial invertebrate inputs were higher in open reaches; however, trends suggested higher biomass of terrestrial inputs in forested reaches and a corresponding higher density of terrestrial prey consumed by water column feeding fishes. Reach-scale biotic integrity (macroinvertebrates, salamanders, and fishes) was largely unaffected by differences in canopy cover. In urbanizing areas where catchment land cover drives habitat and biotic quality, management practices that rely exclusively on forested riparian areas for stream protection are unlikely to be effective at maintaining ecosystem integrity.

scholarly journals Understanding Land Cover Change in a Fragmented Forest Landscape in a Biodiversity Hotspot of Coastal Ecuador

2018 ◽  
Vol 10 (12) ◽  
pp. 1980 ◽  
Author(s):  
Xavier Haro-Carrión ◽  
Jane Southworth
Keyword(s):  
Land Cover ◽  
Forest Cover ◽  
Secondary Forest ◽  
Dry Forest ◽  
Training Data ◽  
Forest Types ◽  
Landsat Images ◽  
Old Growth ◽  
Plantation Forests ◽  
Forest Regrowth

Understanding forest cover changes is especially important in highly threatened and understudied tropical dry forest landscapes. This research uses Landsat images and a Random Forest classifier (RF) to map old-growth, secondary, and plantation forests and to evaluate changes in their coverage in Ecuador. We used 46 Landsat-derived predictors from the dry and wet seasons to map these forest types and to evaluate the importance of having seasonal variables in classifications. Initial RF models grouped old-growth and secondary forest as a single class because of a lack of secondary forest training data. The model accuracy was improved slightly from 92.8% for the wet season and 94.6% for the dry season to 95% overall by including variables from both seasons. Derived land cover maps indicate that the remaining forest in the landscape occurs mostly along the coastline in a matrix of pastureland, with less than 10% of the landscape covered by plantation forests. To obtain secondary forest training data and evaluate changes in forest cover, we conducted a change analysis between the 1990 and 2015 images. The results indicated that half of the forests present in 1990 were cleared during the 25-year study period and highlighted areas of forest regrowth. We used these areas to extract secondary forest training data and then re-classified the landscape with secondary forest as a class. Classification accuracies decreased with more forest classes, but having data from both seasons resulted in higher accuracy (87.9%) compared to having data from only the wet (85.8%) or dry (82.9%) seasons. The produced cover maps classified the majority of previously identified forest areas as secondary, but these areas likely correspond to forest regrowth and to degraded forests that structurally resemble secondary forests. Among the few areas classified as old-growth forests are known reserves. This research provides evidence of the importance of using bi-seasonal Landsat data to classify forest types and contributes to understanding changes in forest cover of tropical dry forests.

Forest Management In Mongolia – A Review Of Challenges And Lessons Learned With Special Reference To Degradation And Deforestation

2019 ◽  
Vol 12 (3) ◽  
pp. 133-166 ◽  
Author(s):  
Alexander Gradel ◽  
Gerelbaatar Sukhbaatar ◽  
Daniel Karthe ◽  
Hoduck Kang
Keyword(s):  
Forest Management ◽  
Land Management ◽  
Management Practices ◽  
Forest Health ◽  
Hydrological Regime ◽  
Lessons Learned ◽  
Ecosystem Functions ◽  
Special Focus ◽  
Driven System ◽  
The Status

The natural conditions, climate change and socio-economic challenges related to the transformation from a socialistic society towards a market-driven system make the implementation of sustainable land management practices in Mongolia especially complicated. Forests play an important role in land management. In addition to providing resources and ecosystem functions, Mongolian forests protect against land degradation.We conducted a literature review of the status of forest management in Mongolia and lessons learned, with special consideration to halting deforestation and degradation. We grouped our review into seven challenges relevant to developing regionally adapted forest management systems that both safeguard forest health and consider socio-economic needs. In our review, we found that current forest management in Mongolia is not always sustainable, and that some practices lack scientific grounding. An overwhelming number of sources noticed a decrease in forest area and quality during the last decades, although afforestation initiatives are reported to have increased. We found that they have had, with few exceptions, only limited success. During our review, however, we found a number of case studies that presented or proposed promising approaches to (re-)establishing and managing forests. These studies are further supported by a body of literature that examines how forest administration, and local participation can be modified to better support sustainable forestry. Based on our review, we conclude that it is necessary to integrate capacity development and forest research into holistic initiatives. A special focus should be given to the linkages between vegetation cover and the hydrological regime.

scholarly journals Investigating impact of land-use and land cover changes on hydro-ecological balance using GIS: insights from IIT Bombay, India

2021 ◽  
Vol 3 (3) ◽  
Author(s):  
Aman Srivastava ◽  
Pennan Chinnasamy
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Surface Runoff ◽  
Forest Cover ◽  
Google Earth ◽  
Negative Consequences ◽  
Ecological Stability ◽  
Barren Land ◽  
Ecological Balance ◽  
Lulc Changes

AbstractThe present study, for the first time, examined land-use land cover (LULC), changes using GIS, between 2000 and 2018 for the IIT Bombay campus, India. Objective was to evaluate hydro-ecological balance inside campus by determining spatio-temporal disparity between hydrological parameters (rainfall-runoff processes), ecological components (forest, vegetation, lake, barren land), and anthropogenic stressors (urbanization and encroachments). High-resolution satellite imageries were generated for the campus using Google Earth Pro, by manual supervised classification method. Rainfall patterns were studied using secondary data sources, and surface runoff was estimated using SCS-CN method. Additionally, reconnaissance surveys, ground-truthing, and qualitative investigations were conducted to validate LULC changes and hydro-ecological stability. LULC of 2018 showed forest, having an area cover of 52%, as the most dominating land use followed by built-up (43%). Results indicated that the area under built-up increased by 40% and playground by 7%. Despite rapid construction activities, forest cover and Powai lake remained unaffected. This anomaly was attributed to the drastically declining barren land area (up to ~ 98%) encompassing additional construction activities. Sustainability of the campus was demonstrated with appropriate measures undertaken to mitigate negative consequences of unwarranted floods owing to the rise of 6% in the forest cover and a decline of 21% in water hyacinth cover over Powai lake. Due to this, surface runoff (~ 61% of the rainfall) was observed approximately consistent and being managed appropriately despite major alterations in the LULC. Study concluded that systematic campus design with effective implementation of green initiatives can maintain a hydro-ecological balance without distressing the environmental services.

Fully automated contrast and non-contrast cardiac view detection in echocardiography a multi-centre, multi-vendor study

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
S Gao ◽  
D Stojanovski ◽  
A Parker ◽  
P Marques ◽  
S Heitner ◽  
...  
Keyword(s):  
Neural Network ◽  
Training Data ◽  
Classification Model ◽  
Validation Dataset ◽  
Funding Source ◽  
Private Company ◽  
Validation Data ◽  
Independent Test ◽  
Model Training ◽  
Confusion Matrices

Abstract Background Correctly identifying views acquired in a 2D echocardiographic examination is paramount to post-processing and quantification steps often performed as part of most clinical workflows. In many exams, particularly in stress echocardiography, microbubble contrast is used which greatly affects the appearance of the cardiac views. Here we present a bespoke, fully automated convolutional neural network (CNN) which identifies apical 2, 3, and 4 chamber, and short axis (SAX) views acquired with and without contrast. The CNN was tested in a completely independent, external dataset with the data acquired in a different country than that used to train the neural network. Methods Training data comprised of 2D echocardiograms was taken from 1014 subjects from a prospective multisite, multi-vendor, UK trial with the number of frames in each view greater than 17,500. Prior to view classification model training, images were processed using standard techniques to ensure homogenous and normalised image inputs to the training pipeline. A bespoke CNN was built using the minimum number of convolutional layers required with batch normalisation, and including dropout for reducing overfitting. Before processing, the data was split into 90% for model training (211,958 frames), and 10% used as a validation dataset (23,946 frames). Image frames from different subjects were separated out entirely amongst the training and validation datasets. Further, a separate trial dataset of 240 studies acquired in the USA was used as an independent test dataset (39,401 frames). Results Figure 1 shows the confusion matrices for both validation data (left) and independent test data (right), with an overall accuracy of 96% and 95% for the validation and test datasets respectively. The accuracy for the non-contrast cardiac views of &gt;99% exceeds that seen in other works. The combined datasets included images acquired across ultrasound manufacturers and models from 12 clinical sites. Conclusion We have developed a CNN capable of automatically accurately identifying all relevant cardiac views used in “real world” echo exams, including views acquired with contrast. Use of the CNN in a routine clinical workflow could improve efficiency of quantification steps performed after image acquisition. This was tested on an independent dataset acquired in a different country to that used to train the model and was found to perform similarly thus indicating the generalisability of the model. Figure 1. Confusion matrices Funding Acknowledgement Type of funding source: Private company. Main funding source(s): Ultromics Ltd.

scholarly journals Classification of Very-High-Spatial-Resolution Aerial Images Based on Multiscale Features with Limited Semantic Information

2021 ◽  
Vol 13 (3) ◽  
pp. 364
Author(s):  
Han Gao ◽  
Jinhui Guo ◽  
Peng Guo ◽  
Xiuwan Chen
Keyword(s):  
Deep Learning ◽  
Land Cover ◽  
Spatial Resolution ◽  
Large Scale ◽  
High Spatial Resolution ◽  
Training Data ◽  
Aerial Images ◽  
Rural Landscapes ◽  
Feature Representations ◽  
Object Based

Recently, deep learning has become the most innovative trend for a variety of high-spatial-resolution remote sensing imaging applications. However, large-scale land cover classification via traditional convolutional neural networks (CNNs) with sliding windows is computationally expensive and produces coarse results. Additionally, although such supervised learning approaches have performed well, collecting and annotating datasets for every task are extremely laborious, especially for those fully supervised cases where the pixel-level ground-truth labels are dense. In this work, we propose a new object-oriented deep learning framework that leverages residual networks with different depths to learn adjacent feature representations by embedding a multibranch architecture in the deep learning pipeline. The idea is to exploit limited training data at different neighboring scales to make a tradeoff between weak semantics and strong feature representations for operational land cover mapping tasks. We draw from established geographic object-based image analysis (GEOBIA) as an auxiliary module to reduce the computational burden of spatial reasoning and optimize the classification boundaries. We evaluated the proposed approach on two subdecimeter-resolution datasets involving both urban and rural landscapes. It presented better classification accuracy (88.9%) compared to traditional object-based deep learning methods and achieves an excellent inference time (11.3 s/ha).

Sign in / Sign up

Export Citation Format

Share Document