KEDR system
What is KEDR system?
The KEDR System is a digital platform created to facilitate forest monitoring. The system is based on an interactive map that visualizes all kinds of data needed to protect forests from illegal logging.
A user of the KEDR system, for example, a forest inspector who plans to patrol a certain area, can get all the available and necessary information right inside the system.
Thanks to this, the forest inspector is freed from a large amount of paperwork and can collect all the necessary information for verification in just a few clicks.
But the main feature of the KEDR system is not even the ability to quickly collect the necessary information, but the presence of signals about changes in the forest. The signals of the KEDR system are generated by a neural network that collects and processes satellite images from different times, and then compares them to identify new "clearings" in the forest canopy. For the analysis, free images of the Landsat satellite with a resolution of 30 meters are used, i.e. one pixel of the image corresponds to an area of 30 by 30 meters.
Thus, forest inspectors planning field raids can see in advance where there have been potential changes in the integrity of the tree canopy and the possibility of illegal logging, which undoubtedly increases the effectiveness of field and raid activities.
How the system work?
Mobile application "Forest Inspector"
Most of the forest resources of the southern Far East are located in remote and hard-to-reach places, where not only the Internet, but also cellular communication is often absent. In order for the inspectors to have access to the information contained in the "KEDR"system in the field, a special mobile application "Forest Inspector"was developed.
The app syncs with the KEDR system and allows to download information about new forest changes to your mobile device. Thanks to this application, forest inspectors and forestry workers can check the signals of the KEDR system in the field, take photos of violations, and save all the necessary information about forest changes and violations of forest legislation.
Checking signals with drones
To facilitate the verification of signals located at a distance from the main roadway, the KEDR system has built-in the ability to check signals using unmanned aerial vehicles (drones).
To do this, simply select the signals that you want to check with the drone, after which the KEDR system will automatically generate and transmit to the drone a flight task that allows you to examine in detail the entire perimeter of the forest massive, which was marked as a forest changes.
The drone in autopilot mode will fly around the place designated as a forest modification. The system forms the flyby trajectory in such a way that as a result of subsequent drone flyby and continuous photofixing, a high-resolution orthophotoplane is formed, tied to the terrain.
Neural networks and the system
Neural networks are data processing systems that are structurally similar to the networks of nerve cells in the human brain. Their main feature is the ability to capture the smallest patterns and relationships (so-called patterns) that may be invisible to the human eye or a traditional computer program; this allows neural networks to classify the analyzed information with amazing accuracy.
Like humans, neural networks are capable of self-learning. For example, if a person is shown several cards with the image of a tree, then in the future he will be able to recognize (classify) other images of trees, even if they differ significantly from the images on which the training was conducted. A similar process occurs with neural networks.
How does it differ from satellite surveillance?
Classical satellite monitoring is based on the so-called change detection systems. These systems are based on a comparison of multi-time snapshots, in which changes are recorded either by a professional decryptor or in automatic mode. Automating the process reduces costs and speeds up the process of detecting changes, but at the same time reduces the quality of decryption. On the other hand, the involvement of people in the decryption process, although it improves the quality of the analysis, is associated with significant labor costs, which is reflected in the cost of analysis.
In the KEDR system, the role of a professional decoder is performed by a neural network, which allows you to combine the advantages of automatic and "manual" detection of changes. Image analysis on large areas is not only fast, but also high-quality.
Another important difference between the KEDR system and classical change detection systems is the approach to image comparison. In classical systems, two snapshots are compared, while the KEDR system first forms a so-called "stack", and only after that its attributes are compared with the attributes of the last operational snapshot.
In the classical approach, the pixel colors of the two images are directly compared, while when forming a stack, all images available for a given territory are first collected, after which the median (predicted) color value is determined, and then a comparison is made with the color of the last image.
How are new signals formed?
The KEDR System automatically checks the updates of satellite images of Landsat-8 and Landsat-7, if new images are available, the process of finding changes is launched. At the first stage, images are prepared: the system, using a special algorithm, "cleans" images from clouds, water bodies and shadows that can interfere with analysis.
In the figure, an example of a cloud mask created. Red shows the contours of clouds and shadows cast by clouds. These areas are excluded from further analysis
In the next step, the system prepares the stack. To do this, using the so-called harmonic model based on historical data (images of past years taken in a given area in similar conditions), the system builds forecast values of brightness and indices for each section of the analyzed area based on the position of the satellite camera and the azimuth of the sun.
After that, using a neural network, a pixel-by-pixel comparison of the attributes of new images with the predicted results obtained using a harmonic model (stack) takes place.
When comparing each of the pixels, the system assigns it one of three possible classes:
- «No changes», in the event that the values of brightness and pixel indices in the new image do not differ from the predicted values
- «New changes», in case when the pixel value has changed during the analyzed period
- «Old changes», in case when the pixel value in the new picture differs from the forecast values, however, this change was recorded in the last period.
In the figure, an example of a raster layer with pixels marked as forest changes. Red color corresponds to a high probability of forest changes, orange color - medium.
Loggings that have not been highlighted belong to the old changes.
The result of the neural network is a raster layer in which each pixel is assigned a value from 0 to 100. This figure reflects the confidence of the neural network that a change has occurred in a given pixel. For example, a value of 100 denotes 100 percent confidence of the neural network that a change has occurred in a given pixel.
Area of operations
The KEDR system was launched and officially put into operation in the Primorsky and Khabarovskiy provinces. The territory of the analysis in Primorye is currently represented by three test forest districts (Roshchinsky, Dalnerechensky and Ussuriysky). And until 2021, it is planned to expand the operation zone by three more forest plots (Chuguevskoye, Sergeyevskoye and Kavalerovskoye). In the Khabarovskiy province, the system operates on the territory of six test forest districts (Avanskoye, Bikinskoye, Oborskoye, Khorskoye, Mukhenskoye, and Sukpayskoye).
In total, since the launch of the system (taking into account illegal logging identified during system testing), mobile groups created to work with the CEDAR system, as well as WWF employees, have identified 108 illegal logging with a total volume of about 7 442 m3 and economic loss of 856,2 million rubles.
More specifically:
- At the stage of testing the system in 2015-2017, 37 illegal logging during the growing season and 13 illegal logging during the snowy/leafless period were detected. The total volume of illegal logging amounted to 3 903 m3, and the damage amounted to more than 639,8 million rubles.
- At the stage of using the system in Primorsky provncein the period from 2017 to 2020 44 illegal loggingwas recorded, with a total volume of 1129,72 m3, which caused damage in the amount of 92,5 million rubles.
- At the stage of using the system in the Khabarovsk province for the same period, 14 illegal logging was detected, with a total volume of 2409,27 m3, which caused damage in the amount of 123,9 million rubles.
History of the system development
2014-2016
The KEDR system was developed by the World Wide Fund for Nature in 2014-2015. Already in July 2015, at a meeting of the office of the Presidential Plenipotentiary Representative in the Far Eastern Federal District, it was decided to test the KEDR system in the field. In August-September, such a check on the territory of test forest plots of the Khabarovsky and Primorsky provinces was carried out by employees of the Amur branch of WWF Russia, the Department of Forestry of the Primorsky province and the Forestry Department of the Government of the Khabarovsky province.
Already in the course of field tests of the KEDR system, 11 illegal logging operations were identified, dozens of cubic meters of illegally harvested wood were seized, including a group of persons engaged in illegal logging, as a result of which several units of logging equipment were seized.
2017- til now
Two separate mobile groups were created in both provinces to work directly with the signals of the KEDR system. The WWF provided the teams with cars, tablet computers needed to operate the KEDR system in the field, other equipment and fuel. In addition, the staff of the mobile groups took part in several training seminars on detecting illegal logging and working with the KEDR system.
At the end of 2017, the ability to check signals about changes in the forest using drones (UAV) was introduced into the KEDR system. After testing the new feature of the KEDR system, WWF handed over two drones to the employees of the mobile groups, and also organized training both on creating flight tasks inside the KEDR system, and on piloting drones if it is necessary to switch the drone to manual control.
