HAHasan Aksoy

Hasan Aksoy

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hasan Aksoy has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Aboveground Biomass Estimation in Pure Calabrian Pine Stands of Southern Türkiye Using Multi-Seasonal Sentinel-2 Imagery and Topographic Variables: A Multi-Seasonal Comparison

    by Hasan Aksoy, Joel Kostensalo

    Aboveground biomass (AGB) is considered a key variable in surveilling the sustainability of forest management and the carbon cycle. This study examined the effects of image acquisition season and topographic variables on the performance of AGB estimates using Sentinel-2 imagery from three seasons. The study was conducted in 224 sample plots in pure Calabrian pine (Pinus brutia) stands in southern Türkiye. Random forest models were trained on 26 datasets derived from rainy, arid, and semi-arid season imagery, including single-season, two-season, and three-season combinations with and without topographic variables. Models trained using satellite images from rainy and semi-arid seasons performed better than models trained using data from the more arid season. All two-season combinations outperformed the corresponding single-season models, but none reached the accuracy of the three-season model. Including topographic variables reduced RMSE for every season and season combination. The best results were obtained using all three seasons together with topographic variables (R2 = 0.74, RMSE = 13.97 Mg ha−1), and removing topography from this model increased RMSE to 15.69 Mg ha−1. According to the SHAP analysis, elevation was the second-most influential predictor after Aug_SAVI (mean SHAP value = 1.65 Mg ha−1) and the only topographic variable that notably contributed to predictive performance. These findings indicate that, for the pure Calabrian pine stands and conditions examined in this study, combining multi-seasonal Sentinel-2 imagery with topographic variables improves AGB estimation accuracy compared with single-season models and spectral data alone.

  • Open Access

    Prediction of LAI in Scots Pine Forests of Türkiye Using UAV and Sentinel 2 Images

    by Hasan Aksoy, Annika Kangas, Petteri Packalen, Lauri Korhonen, Alkan Günlü

    Monitoring the structural characteristics of vegetation cover is critical for understanding ecosystem functioning and sustainable forest management. Effective Leaf area index (LAIe) is directly related to photosynthetic capacity, carbon cycle, and water balance of ecosystems. In this study, LAIe prediction was performed using random forest algorithms with five different datasets obtained from unmanned aerial vehicle (UAV) images and Sentinel 2 (S2) satellite images. The study aimed to (1) determine which UAV features perform best in the prediction of LAIe, and (2) to compare prediction accuracies obtained while using UAV and S2 features. To evaluate the contribution of different data sources, five datasets were considered, namely UAV_RGB (DS1), UAV_3D (DS2), UAV_ALL (DS3), S2 (DS4), and ALL (DS5), with corresponding RMSE% values of approximately 27.3, 29.6, 24.4, 32.1, and 24.8, respectively. The results showed that the DS3 dataset provided the highest accuracy and the most balanced error distribution. The DS5 resulted in more stable prediction performance compared to individual datasets, enabling the model to demonstrate similar accuracy levels for both low and high LAIe values. We conclude that low‐cost UAV‐RGB data, utilizing both 3D and 2D features, is an effective alternative to high‐cost remote sensing techniques for LAIe prediction.


  • Optimisation of Maslow’s hierarchy of needs-based survey form for nursing home residents using machine learning

    by Nedim Alici, Damla Altuncu, Enes Cengiz, Hasan Aksoy

    The global increase in the elderly population necessitates accurate assessment of the needs of individuals residing in nursing homes. This study aims to optimise a 30-item questionnaire developed on the basis of Maslow's Hierarchy of Needs by employing machine learning algorithms. As one of the pioneering applications in Turkey, the research was conducted with 310 participants from four nursing homes. Data were analysed using Artificial Neural Network (ANN), Gaussian Process Regression (GPR), Linear Regression (LR), and Support Vector Machine (SVM). F-Test results identified the most significant variables, reducing the number of items from 30 to 10. Within the comparative analyses, the GPR model outperformed the others by yielding the lowest mean error metrics (RMSE = 0.252, MSE = 0.064, MAE = 0.195) and the highest predictive accuracy (R2 = 0.86). Findings indicate that the physiological, social, and psychological needs of older adults can be assessed through shorter, more reliable questionnaires. This study offers academic and practical contributions to elderly care and interior design.

  • Sinop Yöresi Saf ve Doğal Sarıçam Meşcereleri için Çap-Boy Modellerinin Geliştirilmesi

    by Hasan Aksoy, Alkan Günlü, Ferhat Bolat

    Bu çalışmada, Sinop yöresi doğal Sarıçam (Pinus sylvestris L.) meşcereleri için çap (D)-boy (H) modelleri geliştirilmiştir. Model geliştirme aşamasında, 184 örnek alandan elde edilen toplam 904 adet D ve H verisi kullanılmıştır. Bununla birlikte çeşitli meşcere değişkenleri de ölçülmüş ve hesaplanmıştır. Çalışma kapsamında sadece çap değişkeni ve çap ile birlikte meşcere değişkenlerini içeren çeşitli model formları dikkate alınmıştır. Geliştirilen modellerin başarısı ve tahmin davranışı çeşitli hata ölçütleri, tahmin-gözlem ve tahmin-hata grafikleri üzerinden değerlendirilmiştir. Elde edilen bulgulara göre, sadece çap değişkenini içeren model ölçülen boy değerlerindeki varyansın önemli bir kısmını açıklasa da hatalarda değişen varyans problemi göstermiştir (Model belirtme katsayısı=0.90). Çap ile birlikte çeşitli meşcere değişkenlerini içeren genelleştirilmiş H-D modelleri ise hem daha iyi bir varyans açıklama değerine sahip (Model belirtme katsayısı=0.94) hem de hatalarda sabit bir varyans göstermiştir. İstatistiksel ve grafiksel değerlendirmelerin sonucu olarak, genelleştirilmiş H-D modellerinin Sinop yöresinde yayılış yapan doğal Sarıçam meşcerelerinde güvenle kullanılabileceği söylenebilir.

  • Open Access

    Evaluation of forest areas and land use/cover (LULC) changes with a combination of remote sensing, intensity analysis and CA-Markov modelling

    by Hasan Aksoy

    Background: Land use and land cover change (LULC) is crucial for maintaining the integrity of ecosystems’ structure and function, and thus regular measurement and monitoring of LULC are necessary. Methods: In this study, the temporal and spatial changes in forest areas and land cover in the province of Sinop, located in the north of Turkey, were analysed by intensity analysis for two 10-year periods from 2002-2012 to 2022, and 2032 and 2042 forecast LULC maps were generated using the cellular automata CA-Markov model. In the study, datasets were prepared using forest type maps and Landsat images, and the images were classified using various classification techniques. Results: The results indicated that forest areas increased by 23% (37,823.38 ha) from 2002 to 2022, with the mixed forest category showing a decrease of 22% (12,245.43 ha) within this. In non-forest areas, a significant increase of 72% was observed in the settlement category, while a decrease of 63% was noted in the agricultural category. According to the intensity analysis, the rate of change in LULC is faster from 2002 to 2012 than from 2012 to 2022. In both periods, the settlement and agricultural categories have predominantly targeted each other’s losses. According to the simulation results of land use/cover from 2022 to 2042, a 0.50% increase in total forest area, a 2.87% increase in settlements, and a decrease of 2.65% and 0.71% in agriculture and water classes, respectively, are anticipated. Conclusions: The overall results suggest that it can contribute to setting an appropriate development goal, especially for forest planners and policymakers, to regulate land use changes to achieve higher carbon stocks and maintain balance in global climate scenarios.


  • Open Access

    Estimation Stand Volume, Basal Area and Quadratic Mean Diameter Using Landsat 8 OLI and Sentinel‐2 Satellite Image With Different Machine Learning Techniques

    by Hasan Aksoy

    The data required for sustainable forest planning is provided by traditional forest inventories, which are labor, time, and cost‐intensive. Providing this data quickly, reliably, and accurately is crucial for planners and researchers. The objective of this study was to predict stand basal area (BA), stand volume (V), and quadratic mean diameter (dq) by leveraging vegetation indices (VIs) and reflectance (R) derived from Landsat 8 OLI and Sentinel 2 satellite images, along with topographic (T) data obtained from ALOS‐PALSAR satellite imagery. Forest inventory data for a total of 250 sample plots were used for modeling in the study. Stand parameters were estimated using support vector machines (SVM), multiple linear regression (MLR), decision tree (DT), and random forest (RF) algorithms. In modeling V, BA, and dq, both individual and combinations of R, VIs, and T values obtained from satellite imagery were used as independent variables. Using the generated datasets, each of the stand parameters was modeled separately with MLR, SVM, RF, and DT algorithms, and the success of the models was compared to determine the modeling technique and dataset with the highest success for the relevant parameter. The results showed that for each stand parameter, the highest model success was achieved in the combined dataset, which was created by combining all datasets. However, in terms of modeling techniques, the highest success for each stand parameter was achieved with different modeling techniques. The highest success for V is obtained in the model using the SVM method (R2 = 0.78; RMSE = 0.28 m3/ha), the RF method yielded the highest model performance for BA (R2 = 0.70; RMSE = 2.53 m2/ha), and finally, the highest success for dq was obtained in the DT method (R2 = 0.74; RMSE = 0.02 cm). In general, the datasets obtained from Sentinel 2 images showed higher model success than the datasets obtained from Landsat 8 OLI images.


  • Open Access

    Investigations of the spatial and climate characteristics of natural pure chestnut (Castanea sativa Mill.) forests: A case of Zonguldak Regional Directorate of Forestry

    by Hasan Aksoy

    Chestnuts with high economic and socio-cultural value (Castanea sativa Mill.) must determine forests' spatial and climatic characteristics to improve them, increase fruit yield, and effectively combat diseases and pests. This study aimed to determine the spatial and climatic attributes of pure chestnut forests spreading within the borders of the Zonguldak Forestry Regional Directorate. A total of six criteria were used for spatial and climatic analyses: total precipitation (mm/year), annual mean temperature (C°), wind speed (m/s), altitude (m), slope (%), and aspect (°). Climate values were calculated as maximum, minimum, and average values, respectively; 1 619.25, 866.95, and 1 024.07 mm/year for total precipitation (mm/year), 13, 6 and 11.76 C° for annual mean temperature (C°), 6.62, 0.22 and 2.46 m/s for wind speed (m/s). The spatial characteristics were calculated as 1 221.68, 33.24, and 300.23 m for the height (m), 32.43%, 7.34%, and 18.63% for the slope (%) and finally, 338.63°, 18.18° and 184.18° for the angle (°), respectively, in terms of maximum, minimum and average values. Bartın Forest Management Directorate (FMD) ranks first with 57.18% of the natural chestnut forests spread the most in the study area, while Zonguldak FMD ranks second with 21.45% and Ulus FMD ranks third with 17.13%. The results obtained from the study based on the location and climate will contribute to the selection of the most suitable place for the new chestnut forest afforestation studies to be established and increase the percentage of success.


  • Open Access

    Flood Risk Analysis with AHP and the Role of Forests in Natural Flood Management: A Case Study from the North of Türkiye

    by Hasan Aksoy

    Aim of studty: The aim of this study is to determine the flood risk map of the study area where floods and flood events are frequently encountered by AHP method. Study area: The study was carried out within the boundaries of the Sinop Regional Directorate of Forestry, Ayancık Forest Management Directorate. Material and method: The flood risk map of the study area was produced by Analytical Hierarchy Process (AHP) method. For AHP, 6 different criteria were used: slope, precipitations, aspect, stream distance, land use, and soil. Forest type maps of the study area were used to analyze the impact of forests on flood risk. In terms of forest structure, the stand structure was divided into 3 classes as coniferous, broadleaf, and mixed forest. Main results: The results showed that flood risk varies with forest structure. Coniferous forest class was determined as the class with the lowest flood risk and mixed forest as the class with the highest flood risk. Research highlights: It was determined that the flood risk changed according to the forest structure. Coniferous forest class was determined as the class with the least flood risk, and mixed forest was determined as the class with the highest flood risk.


  • Determination of landslide susceptibility with Analytic Hierarchy Process (AHP) and the role of forest ecosystem services on landslide susceptibility

    by Hasan Aksoy

    The analysis of landslide susceptibility is a crucial tool in the mitigation and management of ecological and economic hazards. The number of studies examining how the form and durability of forest areas affect landslide susceptibility is very limited. This study was conducted in the Marmara region of northwestern Türkiye, where forested areas and industrial zones are intertwined and dense. The landslide susceptibility map was produced by Analytic Hierarchy Process (AHP) method. In the context of AHP, a total of 12 different variables were employed, namely lithology, slope, curvatures, precipitations, aspect, distance to fault lines, distance to streams, distance to roads, land use, soil, elevation, and Normalized Difference Vegetation Index (NDVI). The performance analysis of the landslide susceptibility map was conducted using the Receiver Operating Characteristics (ROC) curve method. The AUC value was computed (0.809) for the landslide susceptibility map generated by using the AHP technique. Forest type maps were used to analyze the impact of forests on landslide susceptibility. In terms of forest structure, 4 main criteria were determined: stand structure, development stage, crown closure, and stand age. Each criterion was analyzed with Geographic Information Systems (GIS) by overlaying it with the landslide susceptibility map of the study area. The results showed that the risk of landslides was lowest in forests with more than one tree species, mature, development stage and of (e) > 52 cm, and crown closure of 41%—70% (2).