Predicting and correcting vegetation state
Methods and systems for managing vegetation include training a machine learning model based on an image of a training data region before a weather event, an image of the training data region after the weather event, and information regarding the weather event. A risk score is generated for a second region using the trained machine learning model based on an image of the second region and predicted weather information for the second region. The risk score is determined to indicate high-risk vegetation in the second region. A corrective action is performed to reduce the risk of vegetation in the second region.
1. A computer-implemented method for managing vegetation, comprising:
training a machine learning model based on an image of a training data region before a weather event, an image of the training data region after the weather event, and information regarding the weather event, the training including identifying man-made structures in the training data region by comparing a local minimum model and a local maximum model to an elevation model;
generating a risk score for a second region using the trained machine learning model based on an image of the second region and predicted weather information for the second region; and
determining that the risk score indicates high-risk vegetation that poses a risk to a man-made structure in the second region.
2. The method of claim 1 , wherein training the machine learning model comprises determining differences between the image of the training data region before the weather event and the image of the training data region after the weather event.
3. The method of claim 2 , wherein training the machine learning model further comprises identifying changed portions of the training data region as a first type of sample and identifying unchanged portions of the training data region as second type of sample for use as labels during training.
4. The method of claim 1 , wherein training the machine learning model further comprises identifying vegetation in the image of the training data region before the weather event and in the image of the training data region after the weather event.
5. The method of claim 4 , wherein identifying vegetation in an image comprises comparing a local minimum model and a local maximum model of light detection and ranging (LIDAR) information.
6. The method of claim 5 , wherein identifying vegetation in an image further comprises determining that vegetation is present in parts of the image where a difference between the local minimum model and the local maximum model exceeds a threshold.
7. The method of claim 1 , wherein identifying man-made structures in an image further comprises determining that a man-made structure is present in a part of the training data region where the local minimum model and the local maximum model coincide, but are both different from the elevation model.
8. The method of claim 1 , further comprising, performing a corrective action to reduce the risk of vegetation in the second region, wherein the corrective action includes generating a recommendation for vegetation removal to minimize a risk of vegetation damage to a man-made structure.
9. The method of claim 8 , wherein the recommendation includes repeating said generating after vegetation removal has been performed to verify that the high-risk vegetation has been removed.
10. A computer-implemented method for managing vegetation, comprising:
training a machine learning model based on an image of a training data region before a weather event, an image of the training data region after the weather event, and information regarding the weather event, including differences between vegetation shown in the image of the training data region before the weather event and the image of the training data region after the weather event, the training including identifying man-made structures in the training data region by comparing a local minimum model and a local maximum model to an elevation model;
generating a risk score for a second region using the trained machine learning model based on an image of the second region and predicted weather information for the second region; and
determining that the risk score indicates high-risk vegetation that poses a risk to a man-made structure in the second region.
11. A non-transitory computer readable storage medium comprising a computer readable program for managing vegetation, wherein the computer readable program when executed on a computer causes the computer to perform the steps of:
training a machine learning model based on an image of a training data region before a weather event, an image of the training data region after the weather event, and information regarding the weather event, the training including identifying man-made structures in the training data region by comparing a local minimum model and a local maximum model to an elevation model;
generating a risk score for a second region using the trained machine learning model based on an image of the second region and predicted weather information for the second region; and
determining that the risk score indicates high-risk vegetation that poses a risk to a man-made structure in the second region.
12. A system for managing vegetation, comprising:
a model trainer configured to train a machine learning model based on an image of a training data region before a weather event, an image of the training data region after the weather event, and information regarding the weather event, the training including identification of man-made structures in the training data region by comparing a local minimum model and a local maximum model to an elevation model; and
a vegetation manager configured to generate a risk score for a second region using the trained machine learning model based on an image of the second region and predicted weather information for the second region, and to determine that the risk score indicates high-risk vegetation that poses a risk to a man-made structure in the second region.
13. The system of claim 12 , wherein the model trainer is further configured to determine differences between the image of the training data region before the weather event and the image of the training data region after the weather event.
14. The system of claim 13 , wherein the model trainer is further configured to identify changed portions of the training data region as a first type of sample and identifying unchanged portions of the training data region as second type of sample for use as labels during training.
15. The system of claim 12 , wherein the model trainer is further configured to identify vegetation in the image of the training data region before the weather event and in the image of the training data region after the weather event.
16. The system of claim 15 , wherein the model trainer is further configured to compare a local minimum model and a local maximum model of light detection and ranging (LIDAR) information.
17. The system of claim 16 , wherein the model trainer is further configured to determine that vegetation is present in parts of the image where a difference between the local minimum model and the local maximum model exceeds a threshold.
18. The system of claim 12 , wherein the model trainer is further configured to determine that a man-made structure is present in a part of the training data region where the local minimum model and the local maximum model coincide, but are both different from the elevation model.
19. The system of claim 12 , wherein the vegetation manager is further configured to generate a recommendation for vegetation removal to minimize a risk of vegetation damage to a man-made structure.
20. The system of claim 19 , wherein the vegetation manager is further configured to repeat the generation of the risk score after vegetation removal has been performed to verify that the high-risk vegetation has been removed.
21. A system for managing vegetation, comprising:
a model trainer configured to train a machine learning model based on an image of a training data region before a weather event, an image of the training data region after the weather event, and information regarding the weather event, including differences between vegetation shown in the image of the training data region before the weather event and the image of the training data region after the weather event, the training including identification of man-made structures in the training data region by comparing a local minimum model and a local maximum model to an elevation model; and
a vegetation manager configured to generate a risk score for a second region using the trained machine learning model based on an image of the second region and predicted weather information for the second region, and to determine that the risk score indicates high-risk vegetation that poses a risk to a man-made structure in the second region.