Forest Cover Change Detection Research Articles

Forest cover change detection using Normalized Difference Vegetation Index in the Oued Bouhamdane watershed, Algeria - A case study

Forest cover change detection using Normalized Difference Vegetation Index in the Oued Bouhamdane watershed, Algeria - A case study

Coastal forest cover change detection using satellite images and convolutional neural networks in Vietnam

<span lang="EN-US">Monitoring forest cover changes is an important task for forest resource management and planning. In this context, remote sensing images have shown a high potential in forest cover changes detection. In Vietnam, although the existence of a large number of such images and ground-truth labels, current researches still relied on classical methods employed manual indices, such as multi-variant change vector analysis (MVCA) and normalized difference vegetation index. These methods highly require domain knowledge to determine threshold values for forest change that are applicable only for studied areas. Therefore, in this paper, we propose a method to detect coastal forest cover changes, which can exploit available dataset and ground-truth labels. Moreover, the proposed method does not require much domain knowledge. We used multi-temporal Sentinel-2 imagery to train a segmentation model, that is based on the U-Net network. It was used then to detect forest areas at the same location taken at different times. Lastly, we compared obtained results to identify forest disturbances. Experimental results demonstrated that our method provided a high accuracy of 95.4% on the testing set. Furthermore, we compared our model with the MVCA method and found that our model outperforms this popular method by 3.8%.</span>

Pyeo: A Python package for near-real-time forest cover change detection from Earth observation using machine learning

Monitoring forest cover change from Earth observation data streams in near-real-time presents a challenge for automated change detection by way of a continuously updated big dataset. Even though deforestation is a significant global problem, forest cover changes in pairs of subsequent images happen relatively infrequently. Detecting a change can require the download and processing of tens, hundreds or even thousands of images. In geoscientific applications of Earth observation, machine learning algorithms are increasingly used. Once trained, a machine learning model can be applied to new images automatically.This paper introduces the open-access Python 3 package Pyeo - “Python for Earth Observation”. Pyeo provides a set of portable, extensible and modular Python functions for the automation of machine learning applications from Earth observation data streams, including automated search and download functionality, pre-processing and atmospheric correction, re-projection, creation of thematic base layers and machine learning classification or regression. Pyeo enables users to train their own machine learning models and then apply the models to newly downloaded imagery over their area of interest. This paper describes in detail how Pyeo works, its requirements, benefits, and a description of the libraries used. An application to the automated forest cover change detection in a region in Kenya is given. Pyeo can be used on cloud computing architectures such as Amazon Web Services, Microsoft Azure and Google Colab to provide scalable applications and processing solutions for the geosciences.

Siamese Detail Difference and Self-Inverse Network for Forest Cover Change Extraction Based on Landsat 8 OLI Satellite Images

In the context of carbon neutrality, forest cover change detection has become a key topic of global environmental monitoring. As a large-scale monitoring technique, remote sensing has received obvious attention in various land cover observation applications. With the rapid development of deep learning, remote sensing change detection combined with deep neural network has achieved high accuracy. In this paper, the deep neural network is used to study forest cover change with Landsat images. The main research ideas are as follows. (1) A Siamese detail difference neural network is proposed, which uses a combination of concatenate weight sharing mode and subtract weight sharing mode to improve the accuracy of forest cover change detection. (2) The self-inverse network is introduced to detect the change of forest increase by using the sample data set of forest decrease, which realizes the transfer learning of the sample data set and improves the utilization rate of the sample data set. The experimental results on Landsat 8 images show that the proposed method outperforms several Siamese neural network methods in forest cover change extraction.

Forest Cover Change Detection using Geospatial Technologies in Chandaka National Park, Odisha, India

Forest plays a vital role in carbon sequestration and climate regulation. A crucial tool for managing forest, particularly in protected regions, is keeping track of how the land cover changes in natural places. Using geospatial approaches, such as remote sensing and geographic information system (GIS), the present study has revealed spatio-temporal changes in land use categories and forest cover in the Chandaka National Park of Odisha, India, throughout the period of 1980-2020. The Landsat, LISS III and Sentinel satellite images of the year 1980, 2000 and 2020 were utilized respectively to map five land use land cover categories i.e. deciduous broadleaf forest, crop land, mixed forest, scrub land and water bodies in this preserved area. The satellite images were classified using a Supervised Classification method using Maximum Likelihood algorithm and ground control points (GCPs) were used for the spatial statistical analyses. The overall accuracies of the classification method in land cover categories in year 1980, 2000 and 2020 were 90.45%, 92.76% and 94.68%, respectively. Elsewhere, in order to study land use land cover (LULC) change and loss in forest of the Chandaka National Park, LULC classification, per-pixel scales post classification and self-knowledge on the LULC change process were used. The LULC change detection results showed that deciduous broadleaf forest decreased from 179.01 sq. km (76.66%) in 1980 to 132.75 sq. km (56.85%) in 2020, while mixed forest cover increased by 8.17 sq. km (3.50%) in 1980 to 38.84 sq. km (16.63%) in 2020. Crop land, Scrub land and Water bodies were also increased by 3.34%, 3.27% and 0.07%, respectively. Two significant change processes in the area are the logging activities in several places for timber and the conversion of natural forests with plantation. Agriculture expansion in the forest’s periphery is linked to the dramatic decline in forest cover change. The decline in forest cover is also a result of the production of charcoal and lumber exploitation. Overall, our findings indicated that more public awareness and participatory forest management are necessary to preserve Chandaka National Park. This study highlights the use of geospatial technologies in understanding the changes in LULC in the Chandaka National Park.

Forest cover change detection in relation to climate variability and LULC changes using GIS and RS techniques. A case of the Kafa zone, southwest Ethiopia

Forest cover change detection in relation to climate variability and LULC changes using GIS and RS techniques. A case of the Kafa zone, southwest Ethiopia

A three decade assessment of forest cover changes in Nijhum dwip national park using remote sensing and GIS

Forest cover loss has a crucial impact on global climate change. The Nijhum Dwip National Park (NDNP), a deltaic part of the Sundarbans mangrove forest, has changed significantly over the decades. The goal of this study was to detect the decadal changes in forest cover using freely available satellite remote sensing data and GIS tools. A maximum likelihood classification technique was used to classify the Landsat images of 1990, 2001, 2011 and 2020. The potential of NDVI and SAVI-based classification for detection of forest cover changes in comparison to supervised classification was also evaluated. More than 42% of the total forest cover area (1781 ha) has been deforested over the decades between 1990 and 2011. The study also reported that nearly 1235 ha and over 856 ha of forest area disappeared from 4217.5 ha in 1990 to 2982.5 ha and 2126.16 ha in 2001 and 2011, respectively. In contrast, an increase of 310 ha of forest area has been recorded in the last decade, from 2011 to 2020. NDVI performed better in forest cover change detection than SAVI. This research will be invaluable for this type of research continuity and proper monitoring of this protected mangrove forest area, along with providing useful information to decision makers.

Geospatial Approach for the Analysis of Forest Cover Change Detection using Machine Learning

Spatial data classification is famous over recent years in order to extract knowledge and insights into the data. It occurs because vast experimentation was used with various classifiers, and significant improvement was examined in accuracy and performance. This study aimed to analyze forest cover change detection using machine learning. Supervised and unsupervised learning methods were used to analyze spatial data. A Vector machine was used to support the supervised learning, and a neural network method was used to support unsupervised learning. The Normalized Difference Vegetation Index (NDVI) was used to identify the bands and extract pixel information relevant to the vegetation. The supervised method shows better results because of its robust performance and better analysis of spatial data classification using vegetation index. The proposed system experimentation was implemented by analyzing the results obtained from Support Vector Machine (SVM) and NN (Neural Network) methods. It is demonstrated in the results that the use of NDVI mainly enhances the performance and increases the classifier's accuracy to a greater extent.
 Keywords: Spatial data; Normalized Difference Vegetation Index; NDVI;Vegetation index, Support Vector Machine; Neural Network; Forest Cover Change
 Copyright (c) 2020 Geosfera Indonesia Journal and Department of Geography Education, University of Jember
 This work is licensed under a Creative Commons Attribution-Share A like 4.0 International License

Mangrove Forest Cover Change Detection Along the Coastline of Trincomalee District, Sri Lanka Using GIS and Remote Sensing Techniques

Mangroves provide valuable services to the coastal community in Trincomalee District despite they distributed in the small area. The objectives of this research are to map out the distribution of the mangroves and to detect the change in mangroves in Trincomalee District during the last 20 years. According to this study the reduction in the extent of mangroves caused by clearance for alternative land use including aquaculture, tourism. The total extent of mangroves in Trincomalee district was estimated using Landsat satellite imageries 1997 and 2017. The medium resolution of Landsat imageries may lead to underestimating relatively small, linear mangroves in coastal line of Trincomalee district. The occurrence of clouds in the coastal area can cause data gaps during analysis. This study estimated total mangroves in Trincomalee district was 20.26km2 and 15.07 km2 in 1997 and 2017 respectively and representing a loss of 5.19 km2 in the 20 years (1997-2017). Mangroves loss in the study area varied both spatially and temporally due to differences in habitat alteration pattern. However, Landsat images adequately aided to detect changes in mangroves in Trincomalee district which shows the rate of decline in mangroves.

Multi-temporal forest cover change detection in the Metchie-Ngoum Protection Forest Reserve, West Region of Cameroon

Globally, forest reserves are threatened by human induced deforestation and forest degradation. Within the Congo Basin, substantial deforestation has been quantified over the past years following the recent advancement in remote sensing and GIS applications in forestry research. Satellite images and ground based data are used to map deforestation, forest degradation and disturbances and their corresponding drivers. In Cameroon, recent studies show a general increase in deforestation over the past years. In most forest reserves of the Western Highlands, forest cover loss is basically as a result of rising population of in-situ and nearby settled communities. The Metchie-Ngoum Protection Forest Reserve (PFR) is but one. The study evaluates forest cover changes in the Metchie-Ngoum PFR using remote sensing and ground observations. It was revealed that forest cover though remained relatively stable over the study period (1984–2015), witnessed much degradation resulting to 36.11% estimated secondary forest cover by 1984. Secondary forest also experienced a cumulative loss to clearings/farms and built-up area from 1984 to 2000. The year 2000 was the most alarming. Forest loss is linked to oil palm expansion, increase population and built-up area and settlement related activities like logging. Faced with such rising threat on forest reserves, only a concerted action can guide sustainable forest management and conservation. The study thus recommends the design and implementation of a guided forest conservation policy which gradually applies proper sensitization, frequent visits by eco-guards, less intimidation, participatory forest mapping and the incorporation of forest communities in the sustainable management of forest reserves.

Forest Cover Monitoring and Prediction in A Lesser Himalayan Elephant Landscape

We have monitored the forest cover depletion in parts of Assam and Arunachal Pradesh over an area of 42,375 km 2 in an elephant landscape falling in the Lesser Himalaya, North East India and report the results here. The US Army topographic maps (1924) and multi-date satellite images (1975, 1990, 2000 and 2009) were visually interpreted on-screen for post-classification comparison and forest cover change detection. The exercise showed continuous high loss of forest cover during the study period. A land area having 17,846.27 km 2 forest in 1924 was depleted to 12,514.56 km 2 by 1975, 11,861.75 km 2 by 1990, 10,808.92 km 2 by 2000 and 10,256.58 km 2 by 2009, thereby indicating a constant decrease in forest cover by 12.59%, 1.54%, 2.48% and 1.31% respectively. The total loss in forest cover was estimated to be about 7590 km 2 from 1924 to 2009. The Cellular Automata Markov Model has predicted a further likely decrease of 9007.14 km 2 by 2028. In general, more districts of Assam than Arunachal Pradesh and more plains than hills faced deforestation. We have identified increasing human population and subsequent demand on the land for cultivation as major reasons for forest cover depletion.

Mapping of landscape structure and forest cover change detection in the mountain chains around Addis Ababa: The case of Wechecha Mountain, Ethiopia

Addis Ababa, the capital city of Ethiopia is, a tropical city, found on a high elevation between 2000 m and 3000 m above sea level. The city is bordered by high rise mountains, Entoto Mountain in the North, Wechecha Mountain in the West, Furi Mountain in the South and Yerer Mountain in the East which have a crucial influence on determining the climate of the city. This study, therefore, focuses on landscape structure and forest cover change on Mount Wechecha, which has a great contribution in the regulation of modifying micro climate of the city and the environ, not only due to its elevation but also due to its dense forest cover. Monitoring land cover changes in a mountain ecosystem help to understand and pinpoint the strategy to be followed for the conservation of ecosystems found on the neighbouring mountains, which also have a great influence on regulating the climate of the city. The study uses five Landsat satellite images to derive land cover of Mount Wechecha from 1973 to 2013. Landscape structures and matrixes have been analyzed and mapped based on the patch-corridor-matrix ecological model. The results have shown that the patch analyst result is proportional to the land cover classes derived from the satellite image. The landscape structure indices of the number of patches are decreasing in all years, except for water and settlement. The forest patches are dissolved into agricultural lands. The mean core area of the forest that increases indicates that the forest coverage is limited to certain places. The Mean Core Area of agricultural land decreased in the last decade due to the agricultural land being interrupted by other economic activities, which leads to landscape modifications. Shannon's evenness and diversity index was zero. The overall result indicates that the forest, which play a great role in climate regulation and open land coverages are decreasing at a faster rate (30% and 24.5% in 1973–14% and 2.4%. in 2013 respectively), while settlement is highly increasing (from 1.3% to 26.25% same period). Hence, the priority has to be given to protecting forest loss of Mount Wechecha and other forests on the neighbouring mountains surrounding Addis Ababa in order to have favorable climate conditions in the city. Such type of studies on mountain chains are very vital in considering appropriate environmental planning mechanisms and to formulate policies at the landscape level.

Landsat time series analysis for temperate forest cover change detection in the Sierra Madre Occidental, Durango, Mexico

The Sierra Madre Occidental (SMO) is the longest continuous mountain complex in Mexico and is characterised by high species diversity and a high proportion of endemism. The rate of deforestation is high in Mexico, as in other megadiverse countries, and protection of the country’s biodiversity is a top priority. Quantification of changes in vegetation cover is essential for this purpose. Temporal information is required to enable classification of vegetation cover and change processes. In this study, the disturbances that occurred in the temperate forest of the SMO in the State of Durango (Mexico) during the period 1986–2012 were quantified using Landsat Time Series Stacks (LTSS) and the Vegetation Change Tracker (VCT) algorithm. The results obtained confirmed that land cover changes were detected with high overall accuracy (97.6%). In order to analyze the forest losses corresponding to the only official data available in Mexico, we retrieved land use and vegetation mapping (USV) data from the Mexican National Institute of Statistics and Geography (INEGI). The aridity index was established and fragmentation analysis was carried out in the study area, showing that forest pests and forest fires were the principal disturbance events in the SMO of Durango, and that the climate greatly influenced the occurrence of disturbances. The LTSS-VCT analysis revealed that for the period 1986–2012, about 34% of the temperate forest cover in the SMO in Durango was lost due to different types of disturbance, representing an annual rate of loss of forest cover of 1.3% and affecting 32,840 ha of land per year. The trend analysis of USV data showed very similar changes to those indicated by the LTSS-VCT analysis in terms of loss of temperate forest. However, differences were observed in regards to the absolute values of forest cover and vegetation loss, with analysis of the USV data indicating forest losses of 28% due to disturbances and an annual disturbance rate of 1%, affecting 49,940 ha of land per year. The LTSS-VCT approach proved efficient for mapping data on forest disturbance acquired by a medium spatial resolution (Landsat) sensor in the SMO in the State of Durango, providing satisfactory results and at low cost.

An Error Model for Mapping Forest Cover and Forest Cover Change Using L-Band SAR

We present an error model for forest cover mapping and change detection with L-band synthetic aperture radar (SAR), which considers measurement noise, forest height, number of images available, and imaging conditions. When applied to a multiseasonal set of Advanced Land Observing Satellite Phased-Array type L-band SAR images acquired over a forest site in southern Sweden, the error model, which is founded on a semiempirical model, suggests that a bitemporal set of cross-polarized L-band backscatter observations is sufficient to detect a forest cover loss of 50% at hectare scale for mature forests. The error probability increases when using co-polarization images, images acquired under adverse imaging conditions, or when detecting forest cover change in a forest of low height. The availability of multitemporal L-band observations is expected to improve forest cover retrieval and change detection, albeit highly correlated forest cover retrieval errors between images acquired within narrow time intervals (e.g., months) pose a limit on the improvements that can be achieved.

Forest Cover Monitoring and Change Detection in Nfifikh Forest (Morocco)

Peri-urban forests are subject to different dynamics due to several factors. Nfifikh forest is a man-made space, located in suburban of Mohammedia City, belonging to Casablanca, Settat Region, and geographically between Casablanca, the economic and business Capital of Morocco and Rabat, the national political capital. Over the past three decades, it has experienced several significant degradations. The aim of this study is to evaluate and quantify the deforestation within the study area using a forest cover change detection of various vegetation indices and subpixel classification to pick out high density plots with Landsat images TM, ETM+ and OLI. Remote sensing is used to highlight the changes caused through Space-Time. This monitoring might help managers to generate forest management plans and to moderate the speed of deforestation and degradation. The results show a significant change in vegetation cover detected between 1987 and 2015. The Density increased in 2001 while it decreased considerably in 2015.

Extending the baseline of tropical dry forest loss in Ghana (1984–2015) reveals drivers of major deforestation inside a protected area

Tropical dry forests experience the highest deforestation rates on Earth, with major implications for the biodiversity of these ecosystems, as well as for its human occupants. Global remote sensing based forest cover data (2000−2012) point to the rapid loss of tropical dry forest in South America and Africa, also, if not foremost, inside formally protected areas. Here, we significantly extend the baseline of tropical dry forest loss inside a protected area in Ghana using a generalizable change detection technique. The forest cover change detection is based on the normalized difference vegetation index (NDVI) derived from historical Landsat data (1984–2015). Field measurements were carried out in dry semi-deciduous forest and in the adjacent savanna and woodland. Estimates of the canopy area index and above ground woody biomass were related to NDVI derived from Landsat 8 data. The change detection indicated significant NDVI decrease in a large area initially covered by tropical dry forest, associated with deforestation. The peak in deforestation was found to have occurred between 1990 and 2002, hereafter, the conservation status of the area was improved. A combination of remote sensing data corroborated by secondary data sources provides evidence for the almost complete clearance of a tropical dry forest inside a strictly protected area, attributable to logging and land clearing for arable farming. The NDVI change detection also revealed NDVI increase in the adjacent woodlands from 2002 to 2015, demonstrating woody encroachment. Historical fire data from the MODIS burned area product indicate that the deforested area experienced a high frequency of anthropogenic burning since 2004, which may have caused further degradation and largely prevents forest regeneration. The results show the ongoing destruction of tropical ecosystems even within ostensibly protected areas and ask for the revision of protection and management strategies of such areas.

Spatial assessment of forest cover and land-use changes in the Hindu-Kush mountain ranges of northern Pakistan

Anthropogenic activities and natural processes are continuously altering the mountainous environment through deforestation, forest degradation and other land-use changes. It is highly important to assess, monitor and forecast forest cover and other land-use changes for the protection and conservation of mountainous environment. The present study deals with the assessment of forest cover and other land-use changes in the mountain ranges of Dir Kohistan in northern Pakistan, using high resolution multi-temporal SPOT-5 satellite images. The SPOT-5 satellite images of years 2004, 2007, 2010 and 2013 were acquired and classified into land-cover units. In addition, forest cover and land-use change detection map was developed using the classified maps of 2004 and2013.The classified maps were verified through random field samples and Google Earth imagery (Quick birds and SPOT-5). The results showed that during the period 2004 to 2013 the area of forest land decreased by 6.4%, however, area of range land and agriculture land have increased by 22.1% and 2.9%, respectively. Similarly, barren land increased by 1.1%, whereas, area of snow cover/glacier is significantly decreased by 21.3%. The findings from the study will be useful for forestry and landscape planning and can be utilized by the local, provincial and national forest departments; and REDD+ policy makers in Pakistan.

A simple method for developing near real-time nationwide forest monitoring for Indonesia using MODIS near- and shortwave infrared bands

ABSTRACTRegarding to the deforestation and forest degradation issue in Indonesia, it is an urgent need to develop near real-time forest monitoring that can be seen by the public to make sure the transparency of forest resources management. Remote-sensing technology seems to be a powerful tool for monitoring and assessing the changes in forest cover immediately. We explored 250 m multi-temporal Moderate Resolution Imaging Spectroradiometer (MODIS) data sets to assign a change of temporal land surface dynamics based on two indices; normalized difference vegetation index (NDVI) and open area index (OAI). The data sets were filtered by two filtering approaches, median moving window and linear interpolation, in order to reduce the overall noise so as not to lose useful information from the time-series data. Our results indicated that the use of MODIS data as a basic information in the near real-time system offers great promise to detect the forest cover change in Indonesia’s forestland, since about 90.07% of area assigned to be a change area had actually changed. Meanwhile, about 34.97% of the forest cover change was not assigned to be a change area by the system. This result showed the need to evaluate the threshold in detecting forest cover change. Although the threshold issue is quite problematic in forest cover change detection, the results show that the methodology proposed in this study provides sufficient and useful information in forest monitoring; this includes the location, time and trajectories of the changes. The results of the detection system developed in this article will be available for potential users.

New forests and Kyoto Protocol carbon accounting: A case study in central Italy

Forest expansion into formerly agricultural land plays a relevant role for generating carbon sinks eligible under afforestation activities in the Kyoto Protocol (KP) carbon accounting framework. This paper provides a methodological framework for the multi-temporal assessment of carbon accumulated in these new forest stands, at the reference years of the KP commitment periods: remote sensing analyses, integrating optical imagery and airborne laser scanning data with field survey, are combined with the carbon simulation model CO2FIX to project carbon changes. The approach is applied to a case study in the central Apennines (Italy) to assess the carbon sink associated to these new forests at the years 2008, 2012 and 2020. The approach is based on forest cover change detection and growing stock mapping, while the multi-temporal carbon sink analysis is performed by means of the CO2FIX model. In the considered test area, the results highlight a compound annual rate of forest expansion equal to 0.26% for the period 1990–2012. The overall carbon stored by the new stands is 21.1Mgha−1 (relative standard error less than 10%) at the year 2012, projected to reach 33.5Mgha−1 at the year 2020.

Multi‐temporal Forest Cover Change and Forest Density Trend Detection in a Mediterranean Environment

AbstractThe loss of forests along with the various types of shrubs in the Mediterranean region is seen as an important driver of climate change and has been repeatedly related with the observed land degradation and desertification in the region. Nevertheless, the extent of woody perennial vegetation cover (WPVC) and its density remain largely unclear. Here, we apply a series of algorithms and methods operationally used in Australia for large‐scale WPVC mapping and monitoring and demonstrate their applicability in the Mediterranean region using a Spanish area as the trial site. Five Landsat TM and ETM+ images from various dates spanning 14 years are used to map changes in the extent of WPVC and to identify areas with a declining, stabilising or recovering trend. Results show that the applied methodology, which incorporates (i) pre‐processing of the Landsat imagery, (ii) a canonical variate analysis to spectrally discriminate between woody and non‐woody land cover types, (iii) a conditional probability network and (iv) spectral indices for mapping woody cover and density trend, is highly successful and well suited for use in Mediterranean environments. A rigorous accuracy assessment is undertaken producing overall accuracies above 97% for both woody and non‐woody cover types and all dates. Results also show that in the area of study, the majority of WPVC disturbances were due to forest fires, which represent the region's most frequent natural and anthropogenic disturbance. This raises significant concerns about the future of the area's WPVC. Regeneration compensated to some degree for the high disturbance rates. Copyright © 2015 John Wiley & Sons, Ltd.