Forest planning involves estimating the biomass of species present in the area.Two fundamental parameters are diameter and height through which it is possible to indirectly estimate of biomass present.Digitalisation o...Forest planning involves estimating the biomass of species present in the area.Two fundamental parameters are diameter and height through which it is possible to indirectly estimate of biomass present.Digitalisation of forestry operations,such as forest planning,is crucial and should be affordable and easy-to-use digital applications and open-source devices.A digital progressive web application(PWA)was designed to record measurements.The app was connected via bluetoot to an open-source IoT digital forestry caliper prototyped by modifying a commercial tree caliper.An economic analysis was carried out considering all costs necessary for the development and operation of the app on smartphones and the preparation of electronic means for creation of the digital caliper.A comparison was made between costs of detecting tree diameters through application of the technology developed compared to costs calculated by applying the use of a dendrometric caliper(three technological levels were considered:L1,L2 and L3).The PWA allowed for easy data entry and viewing,maps and tree densities.The open-source digital caliper showed accuracy and precision comparable with similar commercial devices(1.5%±0.9%and 0.0%±0.9%,respectively).Total time per operator was lower using the digital caliper.From an economic perspective,application of the digital technology was more sustainable than the traditional system.Use of the digital caliper in combination with the web application optimizes detection time of a single tree,and therefore decreases overall cost.展开更多
This paper discussed the function of web service technology in Digital Forestry Platform. The work principle and the system structure of the management mechanism of web service resource were also discussed. The web se...This paper discussed the function of web service technology in Digital Forestry Platform. The work principle and the system structure of the management mechanism of web service resource were also discussed. The web service management architecture was designed and all the workflow under this architecture was elaborated. As an important component of Digital Forestry Support Platform, web service management has provided essential guarantee for the operation of Digital Forestry Platform.展开更多
Diseases caused by invasive pathogens are an increasing threat to forest health,and early and accurate disease detection is essential for timely and precision forest management.The recent technological advancements in...Diseases caused by invasive pathogens are an increasing threat to forest health,and early and accurate disease detection is essential for timely and precision forest management.The recent technological advancements in spectral imaging and artificial intelligence have opened up new possibilities for plant disease detection in both crops and trees.In this study,Dutch elm disease(DED;caused by Ophiostoma novo-ulmi,)and American elm(Ulmus americana)was used as example pathosystem to evaluate the accuracy of two in-house developed high-precision portable hyper-and multi-spectral leaf imagers combined with machine learning as new tools for forest disease detection.Hyper-and multi-spectral images were collected from leaves of American elm geno-types with varied disease susceptibilities after mock-inoculation and inoculation with O.novo-ulmi under green-house conditions.Both traditional machine learning and state-of-art deep learning models were built upon derived spectra and directly upon spectral image cubes.Deep learning models that incorporate both spectral and spatial features of high-resolution spectral leaf images have better performance than traditional machine learning models built upon spectral features alone in detecting DED.Edges and symptomatic spots on the leaves were highlighted in the deep learning model as important spatial features to distinguish leaves from inoculated and mock-inoculated trees.In addition,spectral and spatial feature patterns identified in the machine learning-based models were found relative to the DED susceptibility of elm genotypes.Though further studies are needed to assess applications in other pathosystems,hyper-and multi-spectral leaf imagers combined with machine learning show potential as new tools for disease phenotyping in trees.展开更多
基金supported by the Italian Ministry of Agriculture,Ministry of Agriculture,Food Sovereignty and Forestry(MASAF),National program sub project Precision Forestry(AgriDigit program)(DM 36509.7305.2018 of 20/12/2018).
文摘Forest planning involves estimating the biomass of species present in the area.Two fundamental parameters are diameter and height through which it is possible to indirectly estimate of biomass present.Digitalisation of forestry operations,such as forest planning,is crucial and should be affordable and easy-to-use digital applications and open-source devices.A digital progressive web application(PWA)was designed to record measurements.The app was connected via bluetoot to an open-source IoT digital forestry caliper prototyped by modifying a commercial tree caliper.An economic analysis was carried out considering all costs necessary for the development and operation of the app on smartphones and the preparation of electronic means for creation of the digital caliper.A comparison was made between costs of detecting tree diameters through application of the technology developed compared to costs calculated by applying the use of a dendrometric caliper(three technological levels were considered:L1,L2 and L3).The PWA allowed for easy data entry and viewing,maps and tree densities.The open-source digital caliper showed accuracy and precision comparable with similar commercial devices(1.5%±0.9%and 0.0%±0.9%,respectively).Total time per operator was lower using the digital caliper.From an economic perspective,application of the digital technology was more sustainable than the traditional system.Use of the digital caliper in combination with the web application optimizes detection time of a single tree,and therefore decreases overall cost.
基金One study subject of the National 863 plan "The Study and Application of Digital Forestry Platform" (Number 2003AA209060)
文摘This paper discussed the function of web service technology in Digital Forestry Platform. The work principle and the system structure of the management mechanism of web service resource were also discussed. The web service management architecture was designed and all the workflow under this architecture was elaborated. As an important component of Digital Forestry Support Platform, web service management has provided essential guarantee for the operation of Digital Forestry Platform.
文摘Diseases caused by invasive pathogens are an increasing threat to forest health,and early and accurate disease detection is essential for timely and precision forest management.The recent technological advancements in spectral imaging and artificial intelligence have opened up new possibilities for plant disease detection in both crops and trees.In this study,Dutch elm disease(DED;caused by Ophiostoma novo-ulmi,)and American elm(Ulmus americana)was used as example pathosystem to evaluate the accuracy of two in-house developed high-precision portable hyper-and multi-spectral leaf imagers combined with machine learning as new tools for forest disease detection.Hyper-and multi-spectral images were collected from leaves of American elm geno-types with varied disease susceptibilities after mock-inoculation and inoculation with O.novo-ulmi under green-house conditions.Both traditional machine learning and state-of-art deep learning models were built upon derived spectra and directly upon spectral image cubes.Deep learning models that incorporate both spectral and spatial features of high-resolution spectral leaf images have better performance than traditional machine learning models built upon spectral features alone in detecting DED.Edges and symptomatic spots on the leaves were highlighted in the deep learning model as important spatial features to distinguish leaves from inoculated and mock-inoculated trees.In addition,spectral and spatial feature patterns identified in the machine learning-based models were found relative to the DED susceptibility of elm genotypes.Though further studies are needed to assess applications in other pathosystems,hyper-and multi-spectral leaf imagers combined with machine learning show potential as new tools for disease phenotyping in trees.
