Automatic Windthrow Detection Using Very-High-Resolution Satellite Imagery and Deep Learning

Tropical cyclones moving into boreal forests: Relationships between disturbance areas and environmental drivers

Tropical cyclones (TCs) are common disturbance agents in tropical and subtropical latitudes. With global warming, TCs began to move to northern latitudes, with devastating effects on boreal forests. However, it remains unclear where and when these extraordinary events occur and how they affect forest structure and ecosystem functioning. Hence knowing which geomorphological features, landforms, and forest types are most susceptible to severe wind disturbance is vital to better predict the future impacts of intensifying tropical cyclones on boreal forests. In October 2015, catastrophic TC Dujuan hit the island of Sakhalin in the Russian Far East. With a wind speed of 63 m·s^-1, it became the strongest wind recorded in Sakhalin, damaging >42,000 ha of native forests with different levels of severity. We used high-resolution RGB satellite images, DEM-derived geomorphological patterns, and the U-Net-like convolutional neural network to quantify the damaged area in specific landform, forest type, and windthrow patch size categories. We found that large gaps (>1 ha) represent >40 % of the damaged area while small gaps (<0.1 ha) only 20 %. The recorded canopy gaps are very large for the southern boreal forest. We found that the aspect (slope exposure) is the most important in explaining the damaged area, followed by canopy closure and landform type. Closed-canopy coniferous forests on steep, west-facing slopes (typical of convex reliefs such as ridges, spurs, and peaks) are at a much higher risk of being disturbed by TCs than open-canopy mountain birch forests or coniferous forests and broadleaved riparian forests in concave reliefs such as valley bottoms. We suggest that the projected ongoing poleward migration of TCs will lead to an unprecedentedly large area of disturbed forest, which results in complex changes in forest dynamics and ecosystem functioning. Our findings are crucial for the development of mitigation and adaptation strategies under future changes in TC activity.

Detection of Windthrown Tree Stems on UAV-Orthomosaics Using U-Net Convolutional Networks

The increasing number of severe storm events is threatening European forests. Besides the primary damages directly caused by storms, there are secondary damages such as bark beetle outbreaks and tertiary damages due to negative effects on the market. These subsequent damages can be minimized if a detailed overview of the affected area and the amount of damaged wood can be obtained quickly and included in the planning of clearance measures. The present work utilizes UAV-orthophotos and an adaptation of the U-Net architecture for the semantic segmentation and localization of windthrown stems. The network was pre-trained with generic datasets, randomly combining stems and background samples in a copy–paste augmentation, and afterwards trained with a specific dataset of a particular windthrow. The models pre-trained with generic datasets containing 10, 50 and 100 augmentations per annotated windthrown stems achieved F1-scores of 73.9% (S1Mod10), 74.3% (S1Mod50) and 75.6% (S1Mod100), outperforming the baseline model (F1-score 72.6%), which was not pre-trained. These results emphasize the applicability of the method to correctly identify windthrown trees and suggest the collection of training samples from other tree species and windthrow areas to improve the ability to generalize. Further enhancements of the network architecture are considered to improve the classification performance and to minimize the calculative costs.

Artificial Intelligence for Biology

Despite efforts to integrate research across different subdisciplines of biology, the scale of integration remains limited. We hypothesize that future generations of Artificial Intelligence (AI) technologies specifically adapted for biological sciences will help enable the reintegration of biology. AI technologies will allow us not only to collect, connect and analyze data at unprecedented scales, but also to build comprehensive predictive models that span various subdisciplines. They will make possible both targeted (testing specific hypotheses) and untargeted discoveries. AI for biology will be the cross-cutting technology that will enhance our ability to do biological research at every scale. We expect AI to revolutionize biology in the 21st century much like statistics transformed biology in the 20th century. The difficulties, however, are many, including data curation and assembly, development of new science in the form of theories that connect the subdisciplines, and new predictive and interpretable AI models that are more suited to biology than existing machine learning and AI techniques. Development efforts will require strong collaborations between biological and computational scientists. This white paper provides a vision for AI for Biology and highlights some challenges.

Estimating VAIA Windstorm Damaged Forest Area in Italy Using Time Series Sentinel-2 Imagery and Continuous Change Detection Algorithms

Mapping forest disturbances is an essential component of forest monitoring systems both to support local decisions and for international reporting. Between the 28 and 29 October 2018, the VAIA storm hit the Northeast regions of Italy with wind gusts exceeding 200 km h−1. The forests in these regions have been seriously damaged. Over 490 Municipalities in six administrative Regions in Northern Italy registered forest damages caused by VAIA, that destroyed or intensely damaged forest stands spread over an area of 67,000 km2. The present work tested the use of two continuous change detection algorithms, i.e., the Bayesian estimator of abrupt change, seasonal change, and trend (BEAST) and the continuous change detection and classification (CCDC) to map and estimate forest windstorm damage area using a normalized burned ration (NBR) time series calculated on three years Sentinel-2 (S2) images collection (i.e., January 2017–October 2019). We analyzed the accuracy of the maps and the damaged forest area using a probability-based stratified estimation within 12 months after the storm with an independent validation dataset. The results showed that close to the storm (i.e., 1 to 6 months November 2018–March 2019) it is not possible to obtain accurate results independently of the algorithm used, while accurate results were observed between 7 and 12 months from the storm (i.e., May 2019–October 2019) in terms of Standard Error (SE), percentage SE (SE%), overall accuracy (OA), producer accuracy (PA), user accuracy (UA), and gmean for both BEAST and CCDC (SE < 3725.3 ha, SE% < 9.69, OA > 89.7, PA and UA > 0.87, gmean > 0.83).

Using U-Net-Like Deep Convolutional Neural Networks for Precise Tree Recognition in Very High Resolution RGB (Red, Green, Blue) Satellite Images

Very high resolution satellite imageries provide an excellent foundation for precise mapping of plant communities and even single plants. We aim to perform individual tree recognition on the basis of very high resolution RGB (red, green, blue) satellite images using deep learning approaches for northern temperate mixed forests in the Primorsky Region of the Russian Far East. We used a pansharpened satellite RGB image by GeoEye-1 with a spatial resolution of 0.46 m/pixel, obtained in late April 2019. We parametrized the standard U-Net convolutional neural network (CNN) and trained it in manually delineated satellite images to solve the satellite image segmentation problem. For comparison purposes, we also applied standard pixel-based classification algorithms, such as random forest, k-nearest neighbor classifier, naive Bayes classifier, and quadratic discrimination. Pattern-specific features based on grey level co-occurrence matrices (GLCM) were computed to improve the recognition ability of standard machine learning methods. The U-Net-like CNN allowed us to obtain precise recognition of Mongolian poplar (Populus suaveolens Fisch. ex Loudon s.l.) and evergreen coniferous trees (Abies holophylla Maxim., Pinus koraiensis Siebold & Zucc.). We were able to distinguish species belonging to either poplar or coniferous groups but were unable to separate species within the same group (i.e. A. holophylla and P. koraiensis were not distinguishable). The accuracy of recognition was estimated by several metrics and exceeded values obtained for standard machine learning approaches. In contrast to pixel-based recognition algorithms, the U-Net-like CNN does not lead to an increase in false-positive decisions when facing green-colored objects that are similar to trees. By means of U-Net-like CNN, we obtained a mean accuracy score of up to 0.96 in our computational experiments. The U-Net-like CNN recognizes tree crowns not as a set of pixels with known RGB intensities but as spatial objects with a specific geometry and pattern. This CNN’s specific feature excludes misclassifications related to objects of similar colors as objects of interest. We highlight that utilization of satellite images obtained within the suitable phenological season is of high importance for successful tree recognition. The suitability of the phenological season is conceptualized as a group of conditions providing highlighting objects of interest over other components of vegetation cover. In our case, the use of satellite images captured in mid-spring allowed us to recognize evergreen fir and pine trees as the first class of objects (“conifers”) and poplars as the second class, which were in a leafless state among other deciduous tree species.

Automated Bird Counting with Deep Learning for Regional Bird Distribution Mapping

Simple Summary

To detect changes in migrating bird populations that are usually gradual, regular counts of the flocks should be carried out. This is vital for giving more precise management decisions and taking preventive actions when necessary. Traditional counting methods are widely used. However, these methods can be expensive, time-consuming, and highly dependent on the mental and physical status of the observer and environmental factors. Taking these uncertainties into account, we aimed at taking the advantage of the advances in the artificial intelligence (AI) field for a more standardized counting action. The study has been practically initiated 10 years ago by beginning to take photos on a yearly basis in predefined regions of Turkey. After a large collection of bird photos had been gathered, we predicted the bird counts in photo locations from images by making strong use of AI. Finally, we used these counts to produce several bird distribution maps for further analysis. Our results showed the potential of learning computers in support of real-world bird monitoring applications.

Abstract

A challenging problem in the field of avian ecology is deriving information on bird population movement trends. This necessitates the regular counting of birds which is usually not an easily-achievable task. A promising attempt towards solving the bird counting problem in a more consistent and fast way is to predict the number of birds in different regions from their photos. For this purpose, we exploit the ability of computers to learn from past data through deep learning which has been a leading sub-field of AI for image understanding. Our data source is a collection of on-ground photos taken during our long run of birding activity. We employ several state-of-the-art generic object-detection algorithms to learn to detect birds, each being a member of one of the 38 identified species, in natural scenes. The experiments revealed that computer-aided counting outperformed the manual counting with respect to both accuracy and time. As a real-world application of image-based bird counting, we prepared the spatial bird order distribution and species diversity maps of Turkey by utilizing the geographic information system (GIS) technology. Our results suggested that deep learning can assist humans in bird monitoring activities and increase citizen scientists’ participation in large-scale bird surveys.