Andrii Lashchenko
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Andrii Lashchenko has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Anatolii Makarevych
National University of Life and Environmental Sciences of Ukraine
1 shared publication - Andrii Terentiev
National University of Life and Environmental Sciences of Ukraine
1 shared publication - I. V. Martynchuk
Polissia National University
1 shared publication - Iryna M. Koval
Karazin Institute of Environmental Sciences, V. N. Karazin Kharkiv National University
1 shared publication - Maksym Matsala
Southern Swedish Forest Research Centre, Swedish University of Agricultural Sciences, Alnarp, Sweden
1 shared publication - Nadiya Vasylivna Maksymenko
Karazin Institute of Environmental Sciences, V. N. Karazin Kharkiv National University
1 shared publication
Latest Publications
- Open Access
- 4 November 2026
- Published by IOP Publishing in Environmental Research Letters
- Vol. 21 (21) , 214015
Deep learning reveals severe shelterbelt degradation in eastern Ukraine due to the war
Russia’s full-scale invasion of Ukraine in February 2022 has caused extensive damage to forests, particularly in eastern and southern regions with sustained combat, where field shelterbelts have often been used as cover and subsequently heavily destroyed. This study presents a systematic region-scale assessment of pre-war shelterbelt area and war-related loss between 2021 and 2025 using 3 m PlanetScope imagery and deep learning. We evaluated three input datasets—monthly PlanetScope RGB mosaics, multiseasonal PlanetScope RGB stacks, and surface reflectance (SR) PlanetScope imagery—in combination with two semantic segmentation architectures: a convolutional U-Net with a ResNet-34 encoder and a transformer-based SegFormer with a MiT-B0 backbone. Across all input configurations, the U-Net consistently outperformed SegFormer, achieving the highest F 1 scores. Monthly RGB mosaics delivered accuracy comparable to more complex multiseasonal and SR inputs in pixel-based evaluation and are a cost-efficient option for mapping narrow shelterbelts. The RGB-based model trained on July 2021 mosaics reached an F 1 score of 0.71 and retained values of 0.58–0.67 for other months of the same leaf-on season. Temporal transfer to 2025 resulted in lower but still reasonable performance with F 1 scores of 0.53–0.63. Error-adjusted mapping estimated the shelterbelt area in 2021 at 254 ± 14.5 thousand ha, equivalent to a mean density of 2.6 ha km −2 . By 2025, this area had been reduced by approximately 41 thousand ha, or 16% of the pre-war area. Losses were strongly concentrated along frontlines where local losses exceeded 1.5 ha km −2 compared to an average loss of 0.5 ha km −2 across the entire study area. The resulting maps complement the existing forest monitoring framework in Ukraine and provide a spatially explicit basis for prioritizing post-war remediation and assessing losses in protective functions and carbon accumulation.
- 4 November 2026
- Published by IOP Publishing in Environmental Research Letters
- Vol. 21 (21) , 214015
Open AccessDeep learning reveals severe shelterbelt degradation in eastern Ukraine due to the war
Russia’s full-scale invasion of Ukraine in February 2022 has caused extensive damage to forests, particularly in eastern and southern regions with sustained combat, where field shelterbelts have often been used as cover and subsequently heavily destroyed. This study presents a systematic region-scale assessment of pre-war shelterbelt area and war-related loss between 2021 and 2025 using 3 m PlanetScope imagery and deep learning. We evaluated three input datasets—monthly PlanetScope RGB mosaics, multiseasonal PlanetScope RGB stacks, and surface reflectance (SR) PlanetScope imagery—in combination with two semantic segmentation architectures: a convolutional U-Net with a ResNet-34 encoder and a transformer-based SegFormer with a MiT-B0 backbone. Across all input configurations, the U-Net consistently outperformed SegFormer, achieving the highest F 1 scores. Monthly RGB mosaics delivered accuracy comparable to more complex multiseasonal and SR inputs in pixel-based evaluation and are a cost-efficient option for mapping narrow shelterbelts. The RGB-based model trained on July 2021 mosaics reached an F 1 score of 0.71 and retained values of 0.58–0.67 for other months of the same leaf-on season. Temporal transfer to 2025 resulted in lower but still reasonable performance with F 1 scores of 0.53–0.63. Error-adjusted mapping estimated the shelterbelt area in 2021 at 254 ± 14.5 thousand ha, equivalent to a mean density of 2.6 ha km −2 . By 2025, this area had been reduced by approximately 41 thousand ha, or 16% of the pre-war area. Losses were strongly concentrated along frontlines where local losses exceeded 1.5 ha km −2 compared to an average loss of 0.5 ha km −2 across the entire study area. The resulting maps complement the existing forest monitoring framework in Ukraine and provide a spatially explicit basis for prioritizing post-war remediation and assessing losses in protective functions and carbon accumulation.
- Open Access
- 30 May 2026
- Published by V. N. Karazin Kharkiv National University in Visnyk of V. N. Karazin Kharkiv National University. Series Geology. Geography. Ecology
- No. 64,p. 405-414
Impact of surface fire on the radial growth of Scots pine in Polissya landscapes
Introduction. Forest fires are one of the key destabilizing factors affecting the functioning of forest ecosystems, influencing their productivity, biodiversity, and ecosystem services. Under the conditions of climate change and increasing anthropogenic pressure, particularly due to military actions in Ukraine, the frequency and intensity of fires are rising, which necessitates the study of post‑fire processes in the forests of Polissya. The aim of the research is to determine the patterns of surface fire impact on the radial growth of Scots pine in middle‑aged pine stands of Polissya. Methods. The study is based on a combination of dendrochronological analysis, forest inventory methods, and statistical data processing. Cores were collected from the fire‑damaged stand and from a control (undamaged) stand. Local tree‑ring chronologies were developed, and indexing using moving‑average smoothing was applied. The dynamics of latewood, earlywood, and annual rings were compared between the fire-damaged plot and the control plot for the period 2020–2024. Correlation and regression analyses between growth indices and char height on the stem were performed. Results. A significant reduction in radial growth was found in the year of the fire and in the following period, with a maximum depression in 2023, which was exacerbated by dry climatic conditions. Latewood turned out to be the most sensitive indicator of fire impact, as its width in the damaged stand was significantly smaller compared to the control. Growth recovery for trees that remained viable occurred within two years. A statistically significant relationship was found between latewood indices and char height. Although the char height on the damaged stand varied within the range of 175–250 mm, i.e., the damage can be classified as moderate to severe, the radial growth recovery of the trees that remained alive occurred within two years. This is because the depth of bark charring was shallow, and the middle‑aged pine stands have thick bark that protected the cambium, phloem, and conductive tissues of the wood from fire damage. Moreover, as a result of sanitary felling after the fire, 14% of the trees were lost, which improved light conditions and nutrient availability for the remaining trees. The differences between earlywood and annual ring widths in the damaged stand and the control were insignificant during the pre‑fire period, the year of the fire, and the post‑fire period. The largest - was found for 2023, when the difference was 22%. Analysis of the latewood/earlywood ratio showed a decrease in this index for the damaged plot in the year of the fire (2022) and the first post‑fire year (2023), indicating that this index is suitable for characterizing the impact of stress factors (fires, drought years, etc.) on the radial growth of Scots pine trees. Conclusions. The impact of the 2022 fire on middle-aged Scots pine stands under thermal stress conditions (temperature deviation of +13–28%) was studied. It was found that latewood is the most sensitive indicator of pyrogenic impact: in the year of the fire, its width decreased by 56% (to 0.20±0.04 mm), while earlywood parameters remained stable. A statistically significant regression relationship between latewood indices and char height was revealed. It is proved that if the cambium remains alive, trees restore their radial growth within two years, indicating their resistance.
- 30 May 2026
- Published by V. N. Karazin Kharkiv National University in Visnyk of V. N. Karazin Kharkiv National University. Series Geology. Geography. Ecology
- No. 64,p. 405-414
Open AccessImpact of surface fire on the radial growth of Scots pine in Polissya landscapes
Introduction. Forest fires are one of the key destabilizing factors affecting the functioning of forest ecosystems, influencing their productivity, biodiversity, and ecosystem services. Under the conditions of climate change and increasing anthropogenic pressure, particularly due to military actions in Ukraine, the frequency and intensity of fires are rising, which necessitates the study of post‑fire processes in the forests of Polissya. The aim of the research is to determine the patterns of surface fire impact on the radial growth of Scots pine in middle‑aged pine stands of Polissya. Methods. The study is based on a combination of dendrochronological analysis, forest inventory methods, and statistical data processing. Cores were collected from the fire‑damaged stand and from a control (undamaged) stand. Local tree‑ring chronologies were developed, and indexing using moving‑average smoothing was applied. The dynamics of latewood, earlywood, and annual rings were compared between the fire-damaged plot and the control plot for the period 2020–2024. Correlation and regression analyses between growth indices and char height on the stem were performed. Results. A significant reduction in radial growth was found in the year of the fire and in the following period, with a maximum depression in 2023, which was exacerbated by dry climatic conditions. Latewood turned out to be the most sensitive indicator of fire impact, as its width in the damaged stand was significantly smaller compared to the control. Growth recovery for trees that remained viable occurred within two years. A statistically significant relationship was found between latewood indices and char height. Although the char height on the damaged stand varied within the range of 175–250 mm, i.e., the damage can be classified as moderate to severe, the radial growth recovery of the trees that remained alive occurred within two years. This is because the depth of bark charring was shallow, and the middle‑aged pine stands have thick bark that protected the cambium, phloem, and conductive tissues of the wood from fire damage. Moreover, as a result of sanitary felling after the fire, 14% of the trees were lost, which improved light conditions and nutrient availability for the remaining trees. The differences between earlywood and annual ring widths in the damaged stand and the control were insignificant during the pre‑fire period, the year of the fire, and the post‑fire period. The largest - was found for 2023, when the difference was 22%. Analysis of the latewood/earlywood ratio showed a decrease in this index for the damaged plot in the year of the fire (2022) and the first post‑fire year (2023), indicating that this index is suitable for characterizing the impact of stress factors (fires, drought years, etc.) on the radial growth of Scots pine trees. Conclusions. The impact of the 2022 fire on middle-aged Scots pine stands under thermal stress conditions (temperature deviation of +13–28%) was studied. It was found that latewood is the most sensitive indicator of pyrogenic impact: in the year of the fire, its width decreased by 56% (to 0.20±0.04 mm), while earlywood parameters remained stable. A statistically significant regression relationship between latewood indices and char height was revealed. It is proved that if the cambium remains alive, trees restore their radial growth within two years, indicating their resistance.