Forests are vital ecosystems that play a crucial role in sustaining life on Earth and supporting human well-being.Traditional forest mapping and monitoring methods are often costly and limited in scope,necessitating t...Forests are vital ecosystems that play a crucial role in sustaining life on Earth and supporting human well-being.Traditional forest mapping and monitoring methods are often costly and limited in scope,necessitating the adoption of advanced,automated approaches for improved forest conservation and management.This study explores the application of deep learning-based object detection techniques for individual tree detection in RGB satellite imagery.A dataset of 3157 images was collected and divided into training(2528),validation(495),and testing(134)sets.To enhance model robustness and generalization,data augmentation was applied to the training part of the dataset.Various YOLO-based models,including YOLOv8,YOLOv9,YOLOv10,YOLOv11,and YOLOv12,were evaluated using different hyperparameters and optimization techniques,such as stochastic gradient descent(SGD)and auto-optimization.These models were assessed in terms of detection accuracy and the number of detected trees.The highest-performing model,YOLOv12m,achieved a mean average precision(mAP@50)of 0.908,mAP@50:95 of 0.581,recall of 0.851,precision of 0.852,and an F1-score of 0.847.The results demonstrate that YOLO-based object detection offers a highly efficient,scalable,and accurate solution for individual tree detection in satellite imagery,facilitating improved forest inventory,monitoring,and ecosystem management.This study underscores the potential of AI-driven tree detection to enhance environmental sustainability and support data-driven decision-making in forestry.展开更多
Airborne laser scanning(ALS)has been widely applied to estimate tree and forest attributes,but it can also drive the segmentation of forest areas.Clustering algorithms are the dominant technique in segmentation but sp...Airborne laser scanning(ALS)has been widely applied to estimate tree and forest attributes,but it can also drive the segmentation of forest areas.Clustering algorithms are the dominant technique in segmentation but spatial optimization using exact methods remains untested.This study presents a novel approach to segmentation based on mixed integer programming to create forest management units(FMUs).This investigation focuses on using raster information derived from ALS surveys.Two mainstream clustering algorithms were compared to the new MIP formula that simultaneously accounts for area and adjacency restrictions,FMUs size and homogeneity in terms of vegetation height.The optimal problem solution was found when using less than 150 cells,showing the problem formulation is solvable.The results for MIP were better than for the clustering algorithms;FMUs were more compact based on the intravariation of canopy height and the variability in size was lower.The MIP model allows the user to strictly control the size of FMUs,which is not possible in heuristic optimization and in the clustering algorithms tested.The definition of forest management units based on remote sensing data is an important operation and our study pioneers the use of MIP ALS-based optimal segmentation.展开更多
The use of mobile laser scanning to survey forest ecosystems is a promising,scalable technology to describe forest 3D structures at high resolution.To confirm the con-sistency in the retrieval of forest structural par...The use of mobile laser scanning to survey forest ecosystems is a promising,scalable technology to describe forest 3D structures at high resolution.To confirm the con-sistency in the retrieval of forest structural parameters using hand-held laser scanning(HLS),before operationalizing the method,confirming the data is crucial.We analyzed the per-formance of tree-level mapping based on HLS under differ-ent phenology conditions on a mixed forest in western Spain comprising Pinus pinaster and two deciduous species,Alnus glutinosa and Quercus pyrenaica.The area was surveyed twice during the growing season(July 2022)and once in the deciduous season(February 2022)using several scan-ning paths.Ground reference data(418 trees,15 snags)was used to calibrate the HLS data and to assess the influence of phenology when converting 3D data into tree-level attrib-utes(DBH,height and volume).The HLS-based workflow was robust at isolating tree positions and recognizing stems despite changes in phenology.Ninety-six percent of all pairs matched below 65 cm.For DBH,phenology barely altered estimates.We observed a strong agreement when comparing HLS-based tree height distributions.The values exceeded 2 m when comparing height measurements,confirming height data should be carefully used as reference in remote sensing-based inventories,especially for deciduous species.Tree volume was more precise for pines(r=0.95,and rela-tive RMSE=21.3–23.8%)compared to deciduous species(r=0.91–0.96,and relative RMSE=27.3–30.5%).HLS data and the forest structural complexity tool performed remark-ably,especially in tree positioning considering mixed forests and mixed phenology conditions.展开更多
The deterioration of global environment,decreasing of biological diversity,increasing of natural disasters,exhausting of biological resources and acceleration of desertification emphasize the need to provide the human...The deterioration of global environment,decreasing of biological diversity,increasing of natural disasters,exhausting of biological resources and acceleration of desertification emphasize the need to provide the human-beings with the suitable environments.Nowadays,precision agriculture and precision forestry have been emphasized to obtain the maximum output with minimum input and the least impact on the environment,so agricultural and forestry engineering systems require multi-disciplinary design groups to deal with some common interests and the concept of biomechinfotronics is needed.The word“biomechinfotronic”is introduced to describe the multidisciplinary aspects of this complex system.In the paper,the prospects,mission analysis,education system,research areas of biomechinfotronics are studied.The particular characteristics of biomechinfotronics are the synergistic integration of biological engineering with mechatronics,bioinformatics,infotronics,bioelectronics and intelligent computer systems for conducting common research and development and for recruiting and training students with wide specialties.展开更多
基金funding from Horizon Europe Framework Programme(HORIZON),call Teaming for Excellence(HORIZON-WIDERA-2022-ACCESS-01-two-stage)-Creation of the centre of excellence in smart forestry“Forest 4.0”No.101059985funded by the EuropeanUnion under the project FOREST 4.0-“Ekscelencijos centras tvariai miško bioekonomikai vystyti”No.10-042-P-0002.
文摘Forests are vital ecosystems that play a crucial role in sustaining life on Earth and supporting human well-being.Traditional forest mapping and monitoring methods are often costly and limited in scope,necessitating the adoption of advanced,automated approaches for improved forest conservation and management.This study explores the application of deep learning-based object detection techniques for individual tree detection in RGB satellite imagery.A dataset of 3157 images was collected and divided into training(2528),validation(495),and testing(134)sets.To enhance model robustness and generalization,data augmentation was applied to the training part of the dataset.Various YOLO-based models,including YOLOv8,YOLOv9,YOLOv10,YOLOv11,and YOLOv12,were evaluated using different hyperparameters and optimization techniques,such as stochastic gradient descent(SGD)and auto-optimization.These models were assessed in terms of detection accuracy and the number of detected trees.The highest-performing model,YOLOv12m,achieved a mean average precision(mAP@50)of 0.908,mAP@50:95 of 0.581,recall of 0.851,precision of 0.852,and an F1-score of 0.847.The results demonstrate that YOLO-based object detection offers a highly efficient,scalable,and accurate solution for individual tree detection in satellite imagery,facilitating improved forest inventory,monitoring,and ecosystem management.This study underscores the potential of AI-driven tree detection to enhance environmental sustainability and support data-driven decision-making in forestry.
基金supported by MODFIRE project—A multiple criteria approach to integrate wildfire behavior in forest management planning(PCIF/MOS/0217/2017)benefited from the research exchange platform provided by the Su Fo Run project(Marie SklodowskaCurie Grant Agreement No.691149)。
文摘Airborne laser scanning(ALS)has been widely applied to estimate tree and forest attributes,but it can also drive the segmentation of forest areas.Clustering algorithms are the dominant technique in segmentation but spatial optimization using exact methods remains untested.This study presents a novel approach to segmentation based on mixed integer programming to create forest management units(FMUs).This investigation focuses on using raster information derived from ALS surveys.Two mainstream clustering algorithms were compared to the new MIP formula that simultaneously accounts for area and adjacency restrictions,FMUs size and homogeneity in terms of vegetation height.The optimal problem solution was found when using less than 150 cells,showing the problem formulation is solvable.The results for MIP were better than for the clustering algorithms;FMUs were more compact based on the intravariation of canopy height and the variability in size was lower.The MIP model allows the user to strictly control the size of FMUs,which is not possible in heuristic optimization and in the clustering algorithms tested.The definition of forest management units based on remote sensing data is an important operation and our study pioneers the use of MIP ALS-based optimal segmentation.
文摘The use of mobile laser scanning to survey forest ecosystems is a promising,scalable technology to describe forest 3D structures at high resolution.To confirm the con-sistency in the retrieval of forest structural parameters using hand-held laser scanning(HLS),before operationalizing the method,confirming the data is crucial.We analyzed the per-formance of tree-level mapping based on HLS under differ-ent phenology conditions on a mixed forest in western Spain comprising Pinus pinaster and two deciduous species,Alnus glutinosa and Quercus pyrenaica.The area was surveyed twice during the growing season(July 2022)and once in the deciduous season(February 2022)using several scan-ning paths.Ground reference data(418 trees,15 snags)was used to calibrate the HLS data and to assess the influence of phenology when converting 3D data into tree-level attrib-utes(DBH,height and volume).The HLS-based workflow was robust at isolating tree positions and recognizing stems despite changes in phenology.Ninety-six percent of all pairs matched below 65 cm.For DBH,phenology barely altered estimates.We observed a strong agreement when comparing HLS-based tree height distributions.The values exceeded 2 m when comparing height measurements,confirming height data should be carefully used as reference in remote sensing-based inventories,especially for deciduous species.Tree volume was more precise for pines(r=0.95,and rela-tive RMSE=21.3–23.8%)compared to deciduous species(r=0.91–0.96,and relative RMSE=27.3–30.5%).HLS data and the forest structural complexity tool performed remark-ably,especially in tree positioning considering mixed forests and mixed phenology conditions.
基金the National Natural Science Foundation of China(Programs No.30271078)Jiangsu International Science and Technological Cooperation Project(Project No.BZ2007013)。
文摘The deterioration of global environment,decreasing of biological diversity,increasing of natural disasters,exhausting of biological resources and acceleration of desertification emphasize the need to provide the human-beings with the suitable environments.Nowadays,precision agriculture and precision forestry have been emphasized to obtain the maximum output with minimum input and the least impact on the environment,so agricultural and forestry engineering systems require multi-disciplinary design groups to deal with some common interests and the concept of biomechinfotronics is needed.The word“biomechinfotronic”is introduced to describe the multidisciplinary aspects of this complex system.In the paper,the prospects,mission analysis,education system,research areas of biomechinfotronics are studied.The particular characteristics of biomechinfotronics are the synergistic integration of biological engineering with mechatronics,bioinformatics,infotronics,bioelectronics and intelligent computer systems for conducting common research and development and for recruiting and training students with wide specialties.
