Agronomy

Individual Tree Crown Detection of Palmyrah Palm (Borassus flabellifer) using UAV imagery

2026-08-19T09:24:04Z

Individual Tree Crown Detection of Palmyrah Palm (Borassus flabellifer) using UAV imagery Jeyavanan, K.; Owari, T.; Hiroshima, T.; Nalina, G.; Sivamathy, S.; Kaneswaran, A.; Venugoban, K. 　The Palmyrah palm (Borassus flabellifer) is a multipurpose species highly valued by local communities and often referred to as the “tree of life” due to the extensive use of its various parts. It is predominantly found in the dry zones of Sri Lanka, particularly in the Northern and Eastern regions. However, the current population of Palmyrah palms remains unknown, as manual counting is both labor-intensive and timeconsuming. This study aimed to detect Palmyrah palm in selected areas of the Northern Province of Sri Lanka using unmanned aerial vehicle (UAV) imagery combined with machine learning techniques. The results demonstrated that high-resolution UAV imagery enables accurate detection of Palmyrah palm crowns in the region.

Improving Individual Tree Crown Detection and Species Classification in a Complex Mixed Conifer–Broadleaf Forest Using Two Machine Learning Models with Different Combinations of Metrics Derived from UAV Imagery

2026-08-19T03:16:13Z

Improving Individual Tree Crown Detection and Species Classification in a Complex Mixed Conifer–Broadleaf Forest Using Two Machine Learning Models with Different Combinations of Metrics Derived from UAV Imagery Jeyavanan, K.; Owari, T.; Tsuyuki, S.; Hiroshima, T. Individual tree crown detection (ITCD) and tree species classification are critical for forest inventory, species-specific monitoring, and ecological studies. However, accurately detecting tree crowns and identifying species in structurally complex forests with overlapping canopies remains challenging. This study was conducted in a complex mixed conifer– broadleaf forest in northern Japan, aiming to improve ITCD and species classification by employing two machine learning models and different combinations of metrics derived from very high-resolution (2.5 cm) UAV red–green–blue (RGB) and multispectral (MS) imagery. We first enhanced ITCD by integrating different combinations of metrics into multiresolution segmentation (MRS) and DeepForest (DF) models. ITCD accuracy was evaluated across dominant forest types and tree density classes. Next, nine tree species were classified using the ITCD outputs from both MRS and DF approaches, applying Random Forest and DF models, respectively. Incorporating structural, textural, and spectral metrics improved MRS-based ITCD, achieving F-scores of 0.44–0.58. The DF model, which used only structural and spectral metrics, achieved higher F-scores of 0.62–0.79. For species classification, the Random Forest model achieved a Kappa value of 0.81, while the DF model attained a higher Kappa value of 0.91. These findings demonstrate the effectiveness of integrating UAV-derived metrics and advanced modeling approaches for accurate ITCD and species classification in heterogeneous forest environments. The proposed methodology offers a scalable and cost-efficient solution for detailed forest monitoring and species-level assessment.

Improving the Individual Tree Parameters Estimation of a Complex Mixed Conifer—Broadleaf Forest Using a Combination of Structural, Textural, and Spectral Metrics Derived from Unmanned Aerial Vehicle RGB and Multispectral Imagery

2026-08-19T03:04:32Z

Improving the Individual Tree Parameters Estimation of a Complex Mixed Conifer—Broadleaf Forest Using a Combination of Structural, Textural, and Spectral Metrics Derived from Unmanned Aerial Vehicle RGB and Multispectral Imagery Jeyavanan, K.; Owari, T.; Tsuyuki, S.; Hiroshima, T. Individual tree parameters are essential for forestry decision-making, supporting economic valuation, harvesting, and silvicultural operations. While extensive research exists on uniform and simply structured forests, studies addressing complex, dense, and mixed forests with highly overlapping, clustered, and multiple tree crowns remain limited. This study bridges this gap by combining structural, textural, and spectral metrics derived from unmanned aerial vehicle (UAV) Red–Green–Blue (RGB) and multispectral (MS) imagery to estimate individual tree parameters using a random forest regression model in a complex mixed conifer–broadleaf forest. Data from 255 individual trees (115 conifers, 67 Japanese oak, and 73 other broadleaf species (OBL)) were analyzed. Highresolution UAV orthomosaic enabled effective tree crown delineation and canopy height models. Combining structural, textural, and spectral metrics improved the accuracy of tree height, diameter at breast height, stem volume, basal area, and carbon stock estimates. Conifers showed high accuracy (R2 = 0.70–0.89) for all individual parameters, with a high estimate of tree height (R2 = 0.89, RMSE = 0.85 m). The accuracy of oak (R2 = 0.11–0.49) and OBL (R2 = 0.38–0.57) was improved, with OBL species achieving relatively high accuracy for basal area (R2 = 0.57, RMSE = 0.08m2 tree−1) and volume (R2 = 0.51, RMSE = 0.27 m3 tree−1). These findings highlight the potential of UAV metrics in accurately estimating individual tree parameters in a complex mixed conifer–broadleaf forest.

Comparative Study on the Influence of Liquid Fertilizers on Cabbage Growth and Productivity

2026-08-19T02:36:12Z

Comparative Study on the Influence of Liquid Fertilizers on Cabbage Growth and Productivity Jeyavanan, K.; Pathirana, D.A.; Anusiya, M. The growing emphasis on sustainable agriculture in Sri Lanka has increased interest in liquid fertilizers as eco-friendly alternatives to conventional chemical inputs. To evaluate their effectiveness, a pot experiment was conducted from December 2020 to March 2021 at the Agriculture Farm of the University of Jaffna. This study examined the impact of different liquid fertilizers on the growth and yield of cabbage (Brassica oleracea var. capitata) under insect-proof net house conditions. A Completely Randomized Design (CRD) with ten replicates was used, consisting of four treatments: T1 (control with distilled water), T2 (Nitrobenzene, a chemical growth promoter), T3 (Azolla extract), and T4 (fermented cow urine). Organic treatments were prepared and applied as foliar sprays beginning two weeks after seeding and continued weekly. Statistical analysis (p < 0.05) was performed using SAS software. It revealed that fermented cow urine (T4) significantly enhanced plant height, leaf number, and leaf area, as well as yield attributes such as head diameter, girth, and total yield. Beyond its fertilizing properties, fermented cow urine also acted as a natural pest repellent, contributing to healthier crop growth. These results underscore the potential of fermented cow urine as a cost-effective, eco-friendly alternative for smallholder farmers to improve cabbage production while advancing sustainable farming practices.