17 results about "Forest type" patented technology

The invention relates to the technical field of biological fireproof forests, and discloses a design method for a biological fireproof barrier forest belt, which comprises the following steps of: 1, designing a biological fireproof forest belt based on the canopy density of 0.2-0.5 of a broadleaf mixed forest by taking the existing forest stand type as the broadleaf mixed forest, screening suitable fireproof tree species by integrating site conditions, natural environment and hydrothermal conditions of the biological fireproof forest belt of the broadleaf mixed forest; 2, cleaning and soil preparation are conducted on a biological fireproof forest belt to form a hole belt-shaped area, comprehensive complementary planting is conducted on fireproof tree species, the complementary planting density of a broad-leaf mixed forest is 2520 plants per kilometer as tree planting points, the fireproof tree species are planted in the hole belt-shaped area through the tree planting points, and the fireproof tree species are planted in the hole belt-shaped area; after planting, a compound fertilizer is used for topdressing, so that the fireproof tree seeds absorb fertility to accelerate the growth speed.

The invention relates to the technical field of forest multi-site registration, and discloses a forest multi-site point cloud registration method and related equipment, and aims to construct a feature grid map by fusing multiple classes of semantic tags, avoid registration failure caused by single feature deletion or poor quality, improve the adaptability in multi-forest, multi-season and multi-shielding scenes, and improve the registration accuracy. A high-stability registration area is selected by means of stability scores, self-adaptive adjustment of registration constraints is achieved in combination with a semantic weighting mechanism, the dependence of coarse registration on an initial pose and artificial experience is reduced, and wrong matching interference is reduced. Through semantic weighting ICP fine registration and global optimization, geometric stability differences of different semantic objects are distinguished, unstable structure interference is reduced, and registration precision is improved. Automatic stable registration can be achieved without manual target, the field operation cost and workload are reduced, and large-scale forest scene popularization is facilitated.

The embodiment of the present application provides a method for determining bamboo cultivation target by using the canopy density of upper arbor vegetation type, relates to the technical field of forestry, and evaluates the relevant indexes of the growth of square bamboo planted under different vegetation types in different site conditions, determines the square bamboo cultivation target under the corresponding forest category, forest type and origin of forest in different site conditions according to the evaluation result and the range of the upper arbor canopy that can be adjusted to according to the relevant felling technical regulations, and can also determine the square bamboo cultivation target according to the determined square bamboo cultivation target, and assist in screening the cultivation site by combining factors such as the forest category, forest type and origin, so as to provide a scientific basis for the development planning of bamboo industry.

The invention discloses a forest carbon sink parameter time sequence product generation method, system and device and a storage medium, and is applied to the cross technical field of vegetation remote sensing and carbon cycle monitoring, and the method comprises the steps: obtaining multi-source data of a target region, and generating a vegetation index based on remote sensing data in the multi-source data; based on the vegetation index, constructing a nonlinear model for different forest types, and performing inversion to obtain a corresponding net primary productivity initial time sequence; performing type-oriented differential purification treatment on the initial time sequence of the net primary productivity; feature difference identification is carried out based on the purified time sequence, and the nonlinear model is optimized according to an identification result; generating a net primary productivity time sequence product through the optimized model; according to the method, the problems of mechanism mismatching and information loss when a traditional single model processes heterogeneous forest types are solved, and a high-credibility time sequence parameter product basis is provided for urban forest carbon sink accurate monitoring, operation and management policy making and carbon trading market support.

The invention relates to the technical field of forest carbon reserve prediction and data screening, in particular to a forest carbon reserve estimation method fusing airborne hyperspectral and LiDAR data. The method comprises the following steps: firstly, determining a forest type, and obtaining a carbon reserve estimation model corresponding to each dominant tree species; aiming at various forests, extracting sample plot shapes, sizes and input data corresponding to the carbon reserve estimation models of the forests; the carbon reserve estimation model extracts key features from the input data of the sample plots, and estimates the carbon reserves of the corresponding sample plots based on the key features; and setting a sample plot with a shape and a size corresponding to the carbon reserve estimation model in each forest type, and obtaining a carbon reserve estimation value of the sample plot through the corresponding carbon reserve estimation model. The method can adapt to different forests and automatically adapt to sample plots, and the problems that when the forest carbon reserve is estimated through the remote sensing technology, a LiDAR single data source is relied on, the topographic relation is complex, and the precision is difficult to guarantee are solved.

The invention discloses a carbon sink measurement method and system for a coastal protection forest, and the method comprises the following steps: obtaining field data of a target coastal protection forest, and carrying out the preprocessing of the field data, and obtaining a three-dimensional point cloud model of the protection forest; based on the three-dimensional point cloud model of the protection forest, adaptive forest structure parameter extraction is carried out, and a vegetation type and a corresponding tree height are obtained; the adaptive forest tree structure parameter extraction comprises parameter adaptive single tree segmentation and segmentation-fitting mutual feedback optimization; and performing carbon sink index calculation based on the vegetation type and the corresponding tree height to obtain the carbon density of the protection forest. According to the invention, by introducing a parameter adaptive initialization and segmentation-fitting mutual feedback optimization mechanism driven by a forest type feature vector, internal self-checking and iterative optimization are realized, and an automatic high-precision carbon sink measurement method adaptively coping with changes of arbors and shrubs in a coastal area is realized.

The present application relates to the field of intelligent planting of traditional Chinese medicinal materials and agricultural Internet of Things, and discloses a method for intelligent ecological planting of Morinda officinalis under forest canopy based on environmental monitoring, comprising: S1: determining the target canopy density range based on the forest type, and continuously acquiring the environmental parameters and leaf images of Morinda officinalis growth; S2: implementing ecological improvement of soil under forest canopy and deployment of water regulation infrastructure; S3: identifying and locating the disease spot based on the leaf images, segmenting the disease spot area, extracting the image features and fusing them with the corresponding environmental parameters to construct a multi-source feature set; using the improved NHWOA algorithm to optimize the risk assessment model and output the disease and pest risk grade; S4: making decision based on the real-time environmental parameters and the disease and pest risk grade, generating the regulation instruction and driving the corresponding equipment to execute, and adjusting the decision according to the execution feedback to form a closed loop. The present application realizes real-time sensing and accurate assessment of the microenvironment and disease and pest risk of Morinda officinalis under forest canopy.

The invention relates to the crossing field of traditional Chinese medicinal material intelligent planting and agricultural Internet of Things, and discloses an under-forest intelligent ecological planting method for Cirosa rugosa based on environmental monitoring, which comprises the following steps: S1, determining an adaptive target canopy density range based on a forest stand type, and continuously obtaining environmental parameters and leaf images of growth of Cirosa rugosa; s2, implementing under-forest soil ecological improvement and moisture regulation and control infrastructure deployment; s3, carrying out pest and disease damage identification based on the leaf image and positioning disease spots; segmenting a scab region, extracting image features of the scab region, fusing the image features with corresponding environment parameters, and constructing a multi-source feature set; optimizing the risk assessment model by using an improved NHWOA algorithm, and outputting a disease and pest risk level; and S4, performing decision judgment based on the real-time environment parameters and the disease and insect pest risk levels, generating a regulation and control instruction, driving corresponding equipment to execute, and adjusting a decision according to execution feedback to form a closed loop. According to the invention, real-time perception and accurate evaluation of microenvironment and pest and disease damage risks under the arrowhead forest are realized.

The invention belongs to the technical field of forest remote sensing, and discloses a P-band SAR polarization characteristic-based forest type identification method, which comprises the following steps of: solving a coherence matrix and a covariance matrix on the basis of a pre-processed polarization scattering matrix, and carrying out wavelength dependence correction on basic radar statistical characteristics for a forest three-layer vertical superposition scattering structure formed by a P band; extracting feature subsets of a scattering mechanism related to a forest vertical structure, integrating the corrected basic features and adding polarization phase difference and scattering mechanism combination coefficient feature dimensions to form a complete polarization feature set covering multiple types of features, and extracting various terrain parameters of a target forest region based on DEM data to obtain a complete polarization feature set covering multiple types of features; performing terrain sensitivity analysis on the preliminarily screened feature subset and dividing sensitivity grades, constructing an adaptive terrain correction model in combination with P-band under-forest surface scattering proportion characteristics, and introducing a radar wave polarization state correction term to complete feature radiation normalization correction.

This invention discloses a collaborative inversion method for multiple attributes of individual trees based on transfer learning, relating to the field of forest ecological remote sensing monitoring technology. The method acquires remote sensing images and training samples, generates a canopy height model based on LiDAR point clouds, constructs and trains a single-tree segmentation model based on the U-Net++ architecture, and fine-tunes the encoder weights of the single-tree segmentation model by transferring them to a tree height prediction model and a forest type classification model. Finally, the remote sensing images are input into the three models to obtain the single-tree canopy boundary, predicted tree height, and forest type, and the integrated output is the multi-attribute inversion result for individual trees. This method addresses the problems of complex data dependencies, non-reusable features, low inversion accuracy and efficiency, and easy error accumulation inherent in traditional independent inversion of single-tree attributes.

The invention belongs to the technical field of forestry planting equipment, and discloses a soil loosening device for forestry planting, which mainly comprises a walking bearing mechanism, a self-adaptive adjusting mechanism, a layered soil loosening mechanism and a central control system. The walking bearing mechanism provides a stable moving foundation; the self-adaptive adjusting mechanism integrates a soil parameter sensor and a forest type recognition camera and is used for sensing the working environment in real time. The layered soil loosening mechanism is composed of a twist drill and a shallow soil loosening roller which can be independently regulated and controlled, and collaborative operation is achieved. The device can dynamically adjust the soil loosening strategy and depth according to the parameters of soil hardness, humidity, forest type and the like, and the crossing from mechanization to intelligentization is realized. The beneficial effects are that the elastic soil loosening teeth can effectively prevent nursery stock root system damage, thus protecting soil structure; the operation quality and efficiency are improved through layered soil loosening; the solar power supply and remote monitoring function improves the environmental protection property and the modernization management level of the equipment.

The invention provides a plateau mountain forest type remote sensing classification method and system based on collaborative joint learning, and belongs to the field of forest type identification. The method comprises the following steps: firstly, determining a cartographic geographic area and collecting data; extracting N-dimensional self-supervision features after preprocessing multi-source remote sensing data, and cutting the N-dimensional self-supervision features into standard image blocks after registration; carrying out image block feature fusion to form a self-supervised image block with an N-dimensional space and a self-supervised image block set; constructing first to third self-supervision signals based on the self-integrity and internal relevance of the self-supervision image block set and plateau mountain priori knowledge, and respectively inputting three branches of the self-supervision model to obtain general feature representation; constructing a forest type remote sensing classification model, performing training based on forest type field survey data, and adjusting the general feature representation to a corresponding classification task; and finally, inputting the self-supervised blocks into a classification model to obtain a forest type distribution thematic map, and evaluating the drawing precision. According to the invention, the classification accuracy and precision of forest types are improved.

The invention discloses an under-forest planting method for improving the yield and quality of aralia elata sprouts, and belongs to the technical field of under-forest economic plant cultivation. In order to solve the problem that in the prior art, due to the lack of multi-link integrated optimization of'provenance-habitat-harvesting ', the yield and quality of artificially planted aralia elata sprouts are difficult to synergistically improve and the like, the method comprises the following steps: investigating the yield of wild aralia elata in different regions, the saponin content of wild aralia elata in different forest types and different regions; the method comprises the following steps: selecting an optimal provenance for artificial planting of aralia elata, and preliminarily selecting a suitable forest type; then, the optimal provenance, forest type, canopy density, slope direction and harvesting strategy of artificial planting are determined by researching the influence of different forest types and different canopy densities on the growth and yield of the aralia elata planted artificially, the influence of different slope directions on the growth of the aralia elata and the influence of different harvesting strategies on the overwintering sprouting rate of the aralia elata in the next year; finally, the aralia elata under-forest planting method for simultaneously improving the yield and the quality of the bean sprouts is obtained.

The present application provides a kind of fern composite planting method based on birch forest, and belongs to the technical field of agricultural planting.The present application provides a kind of fern composite planting method based on birch forest in the low-quality birch forest area in northeast forest, solves the problem of low utilization rate of existing low-quality birch forest interspace and unbalanced supply and demand of fern market, and solves the problem of fern resource cultivation and artificial large-area planting difficulty.The present application solves the problem of low-quality birch forest space utilization difficulty by different forest type selection method and different canopy density fern planting method, realizes the one-year two-season harvesting mode of spring vegetable picking and autumn fruit picking by low canopy density plot black bud currant and fern intercropping, increases the utilization efficiency and multiple cropping index of interspace in forest, and provides a new mode for forest economy development and lays a foundation for forest fern industry development.

The present application relates to a kind of dominant tree species BVOCs emission estimation method based on remote sensing biomass inversion, comprising: 1) according to the selection of dominant tree species of forest type in study area;2) for the dominant tree species, selected sample plot in study area and carried out field investigation to obtain the measured parameter related to the above-ground biomass of each dominant tree species;And obtain remote sensing image in study area;3) construct biomass fitting system parameter;4) for each dominant tree species, based on the biomass density of step 3) and remote sensing parameter, with biomass as dependent variable, carry out regression fitting of multiple models;5) establish evaluation index, the accuracy of each model fitting result is evaluated, then the model of optimal accuracy is selected to determine the optimal equation of dominant tree species biomass and vegetation index in study area;6) construct dominant tree species BVOCs emission model based on biomass remote sensing interpretation;And 7) utilize BVOCs emission model to estimate dominant tree species BVOCs emission.

The invention discloses a forest right reform ecological effect evaluation method based on a forest ecosystem service. The method comprises the following steps: S100, determining a main forest type of a research area before forest right reform; s200, the change condition of each main forest type caused by the forest farmer operation behavior is obtained, and a pair of forests and forests is obtained, and the pair of forests and forests comprises two forests related to the change of the main forest type; s300, evaluating ecological system services of the two forest types in the sample plot scale before and after; s400, utilizing a single factor variance analysis method to analyze the influence of the related change of the forest types before and after the forest types on the ecological system service; and S500, carrying out forest ecosystem service evaluation on the research area before and after forest right reform at the area level. According to the method, the forest right reform ecological effect is evaluated from the sample plot scale and the region scale, and a scientific basis can be provided for subsequent forest right reform policy making.

The invention discloses an unmanned aerial vehicle monitoring system for forest carbon sink estimation. The unmanned aerial vehicle monitoring system comprises an unmanned aerial vehicle flight platform, a multi-sensor module, a data transmission module, an edge calculation module, a cloud server and a carbon reserve estimation module. The multi-sensor module is detachably connected to the unmanned aerial vehicle flight platform and used for synchronously collecting multi-dimensional original data of a forest ecosystem, and the multi-sensor module at least comprises a laser radar sensor, a hyperspectral sensor, a thermal infrared sensor and a visible light camera; the edge calculation module is integrated on the unmanned aerial vehicle flight platform. Through fusion of the multi-source sensor, multi-dimensional data such as a three-dimensional structure, biochemical characteristics, thermal characteristics and texture characteristics of a forest can be acquired, and reliable basic data is provided for carbon reserve estimation; local real-time processing of data can be realized through the edge calculation module, so that the processing delay is greatly reduced; and through the carbon reserve estimation module, the estimation precision in different scenes can be ensured according to a forest type optimization model.