Methods and systems for sensor based predictions

1 . A method of using an artificial neural network to improve wildlife management comprising:

receiving, by the artificial neural network, from a plurality of sensors distributed throughout a plurality of sections of a habitat zone, habitat data and wildlife data, wherein the artificial neural network is associated with one or more machine learning models, and wherein at least one first sensor of the plurality of sensors is configured to send the habitat data based on detecting a change in the habitat data that satisfies a first threshold and at least one second sensor of the plurality of sensors is configured to send the wildlife data based on a change in the wildlife data that satisfies a second threshold;

receiving, by the artificial neural network, from a plurality of cameras associated with the plurality of sections of the habitat zone, image data comprising a plurality of images of a species and a plurality of images of a physical area, wherein the plurality of cameras are configured to send the image data based on detecting motion within a field of view of the plurality of cameras and one or more vibrations detected by one or more vibration sensors in communication with the plurality of cameras;

receiving, by the artificial neural network, from the one or more vibration sensors, vibration data;

generating, by a training model of the one or more machine learning models, based on the habitat data, the wildlife data, the image data, the vibration data, and one or more sportsmen profiles, training data configured for training the one or more machine learning models, wherein the one or more machine learning models are configured to determine a predicted population of the species associated with the plurality of sections of the habitat zone;

extracting, by the training model of the one or more machine learning models, one or more sportsmen feature sets from the one or more sportsmen profiles, one or more habitat feature sets from the habitat data, one or more vibration feature sets from the vibration data, and one or more wildlife feature sets from the wildlife data;

combining, by the training model, the one or more habitat feature sets, the one or more wildlife feature sets, the one or more vibration feature sets, and the one or more sportsmen feature sets in a predictive population model;

training, based on the combined feature sets, the predictive population model of the one or more machine learning models using a supervised learning technique, wherein the predictive population model comprises a trained neural network and is configured to predict a population of the species in the plurality of sections of the habitat zone;

determining, by the predictive population model, based on the combined feature sets, the predicted population of the species for each section of the plurality of sections;

determining, by the one or more machine learning models, based on the predicted population of the species for each section of the plurality of sections, a sporting recommendation for the habitat zone, wherein the sporting recommendation indicates a portion of the predicted population of the species that can be consumed for sport within the habitat zone;

determining, by the one or more machine learning models, and based on the sporting recommendation and a predicted hunting license utilization rate, a quantity of hunting licenses to be issued, wherein the predicted hunting license utilization rate is based on historical sportsmen success rates and harvest compliance metrics stored in the one or more sportsmen profiles;

compiling, by the one or more machine learning models, based on the one or more sportsmen profiles, a prioritized list of the one or more sportsmen profiles to be allocated the quantity of hunting licenses, wherein the prioritized list is determined based on at least one of license history data, sporting history data, and conservation history data or donation history data;

issuing, based on the prioritized list, by a computing device in communication with the artificial neural network, the quantity of hunting licenses via one or more printable or digitally distributable license documents;

receiving, by the computing device, post-issuance harvest data from one or more sportsmen of the prioritized list, wherein the post-issuance harvest data indicates whether animals of the species were successfully harvested using the issued quantity of hunting licenses; and

retraining, by the training model of the one or more machine learning models, the predictive population model using the post-issuance harvest data to improve a predictive accuracy of the predictive population model for a subsequent issuance of hunting licenses.

2 . The method of claim 1 , wherein issuing, based on the prioritized list, the quantity of hunting licenses comprises causing paper documentation to be sent to one or more addresses associated with the one or more sportsmen profiles.

3 . The method of claim 1 , wherein the one or more sportsmen profiles comprise data associated with a respective sportsman of a plurality of sportsmen comprising at least one of demographic information, previous sporting information, donation information, or conservation information.

4 . The method of claim 1 , wherein the prioritized list of the one or more sportsmen profiles indicates a probability for each sportsman of a plurality of sportsmen to receive a hunting license of the quantity of hunting licenses.

5 . The method of claim 1 , wherein the prioritized list of the one or more sportsmen profiles comprises one or more priority tiers that are associated with a probability of each sportsman associated with a respective priority tier to be issued a hunting license.

6 . The method of claim 1 , wherein the habitat data indicates a health of a habitat associated with the species, and wherein the wildlife data indicates one or more of: a current population of the species, the predicted population of the species, and/or a sustainable population of the species.

7 . The method of claim 1 , wherein each section of the plurality of sections is defined based on at least one of a topography of the habitat zone, a natural habitat of the species, one or more landmarks, one or more natural boundaries, or one or more manmade boundaries.

8 . An apparatus, comprising:

one or more processors; and

a memory storing processor-executable instructions that, when executed by the one or more processors, cause the apparatus to:

receive, by an artificial neural network, from a plurality of sensors distributed throughout a plurality of sections of a habitat zone, habitat data and wildlife data, wherein the artificial neural network is associated with one or more machine learning models, and wherein at least one first sensor of the plurality of sensors is configured to send the habitat data based on detecting a change in the habitat data that satisfies a first threshold and at least one second sensor of the plurality of sensors is configured to send the wildlife data based on a change in the wildlife data that satisfies a second threshold;

receive, by the artificial neural network, from a plurality of cameras associated with the plurality of sections of the habitat zone, image data comprising a plurality of images of a species and a plurality of images of a physical area, wherein the plurality of cameras are configured to send the image data based on detecting motion within a field of view of the plurality of cameras and one or more vibrations detected by one or more vibration sensors in communication with the plurality of cameras;

receive, by the artificial neural network, from the one or more vibration sensors, vibration data;

generate, by a training model of the one or more machine learning models, based on the habitat data, the wildlife data, the image data, the vibration data, and one or more sportsmen profiles, training data configured for training the one or more machine learning models, wherein the one or more machine learning models are configured to determine a predicted population of the species associated with the plurality of sections of the habitat zone;

extract, by the training model of the one or more machine learning models, one or more sportsmen feature sets from the one or more sportsmen profiles, one or more habitat feature sets from the habitat data, one or more vibration feature sets from the vibration data, and one or more wildlife feature sets from the wildlife data;

combine, by the training model, the one or more habitat feature sets, the one or more wildlife feature sets, the one or more vibration feature sets, and the one or more sportsmen feature sets in a predictive population model;

train, based on the combined feature sets, the predictive population model of the one or more machine learning models using a supervised learning technique, wherein the predictive population model comprises a trained neural network and is configured to predict a population of the species in the plurality of sections of the habitat zone;

determine, by the predictive population model, based on the combined feature set, the predicted population of the species for each section of the plurality of sections;

determine, by the one or more machine learning models, based on the predicted population of the species for each section of the plurality of sections, a sporting recommendation for the habitat zone, wherein the sporting recommendation indicates a portion of the predicted population of the species that can be consumed for sport within the habitat zone;

determine, by the one or more machine learning models, and based on the sporting recommendation and a predicted sporting license utilization rate, a quantity of hunting licenses to be issued, wherein the predicted sporting license utilization rate is based on historical sportsmen success rates and harvest compliance metrics stored in the one or more sportsmen profiles;

compile, by the one or more machine learning models, based on the one or more sportsmen profiles, a prioritized list of the one or more sportsmen profiles to be allocated the quantity of hunting licenses wherein the prioritized list is determined based on at least one of license history data, sporting history data, and conservation history data or donation history data;

issue, based on the prioritized list, by a computing device in communication with the artificial neural network, the quantity of hunting licenses via one or more printable or digitally distributable license documents;

receive, by the computing device, post-issuance harvest data from one or more sportsmen of the prioritized list, wherein the post-issuance harvest data indicates whether animals of the species were successfully harvested using the issued quantity of hunting licenses; and

retrain, by the training model of the one or more machine learning models, the predictive population model using the post-issuance harvest data to improve a predictive accuracy of the predictive population model for a subsequent issuance of hunting licenses.

9 . The apparatus of claim 8 , wherein the processor-executable instructions that, when executed by the one or more processors, cause the apparatus to issue, based on the prioritized list, the quantity of hunting licenses further cause the apparatus to cause paper documentation to be sent to one or more addresses associated with the one or more sportsmen profiles.

10 . The apparatus of claim 8 , wherein the one or more sportsmen profiles comprise data associated with a respective sportsman of a plurality of sportsmen comprising at least one of demographic information, previous sporting information, donation information, or conservation information.

11 . The apparatus of claim 8 , wherein the prioritized list of the one or more sportsmen profiles indicates a probability for each sportsman of a plurality of sportsmen to receive a hunting license of the quantity of hunting licenses.

12 . The apparatus of claim 8 , wherein the prioritized list of the one or more sportsmen profiles comprises one or more priority tiers that are associated with a probability of each sportsman associated with a respective priority tier to be issued a hunting license.

13 . The apparatus of claim 8 , wherein the habitat data indicates a health of a habitat associated with the species, and wherein the wildlife data indicates one or more of: a current population of the species, the predicted population of the species, and/or a sustainable population of the species.

14 . The apparatus of claim 8 , wherein each section of the plurality of sections is defined based on at least one of a topography of the habitat zone, a natural habitat of the species, one or more landmarks, one or more natural boundaries, or one or more manmade boundaries.

15 . One or more non-transitory computer readable media storing processor-executable instructions that, when executed by at least one processor, cause the

at least one processor to:

receive, by an artificial neural network, from a plurality of sensors distributed throughout a plurality of sections of a habitat zone, habitat data and wildlife data, wherein the artificial neural network is associated with one or more machine learning models, and wherein at least one first sensor of the plurality of sensors is configured to send the habitat data based on detecting a change in the habitat data that satisfies a first threshold and at least one second sensor of the plurality of sensors is configured to send the wildlife data based on a change in the wildlife data that satisfies a second threshold;

receive, by the artificial neural network, from a plurality of cameras associated with the plurality of sections of the habitat zone, image data comprising a plurality of images of a species and a plurality of images of a physical area, wherein the plurality of cameras are configured to send the image data based on detecting motion within a field of view of the plurality of cameras and one or more vibrations detected by one or more vibration sensors in communication with the plurality of cameras;

receive, by the artificial neural network, from the one or more vibration sensors, vibration data;

generate, by a training model of the one or more machine learning models, based on the habitat data, the wildlife data, the image data, the vibration data, and one or more sportsmen profiles, training data configured for training the one or more machine learning models, wherein the one or more machine learning models are configured to determine a predicted population of the species associated with the plurality of sections of the habitat zone;

extract, by the training model of the one or more machine learning models, one or more sportsmen feature sets from the one or more sportsmen profiles, one or more habitat feature sets from the habitat data, one or more vibration feature sets from the vibration data, and one or more wildlife feature sets from the wildlife data;

combine, by the training model, the one or more habitat feature sets, the one or more wildlife feature sets, the one or more vibration feature sets, and the one or more sportsmen feature sets in a predictive population model;

train, based on the combined feature sets, the predictive population model of the one or more machine learning models using a supervised learning technique, wherein the predictive population model comprises a trained neural network and is configured to predict a population of the species in the plurality of sections of the habitat zone;

determine, by the predictive population model, based on the combined feature set, the predicted population of the species for each section of the plurality of sections;

determine, by the one or more machine learning models, based on the predicted population of the species for each section of the plurality of sections, a sporting recommendation for the habitat zone, wherein the sporting recommendation indicates a portion of the predicted population of the species that can be consumed for sport within the habitat zone;

determine, by the one or more machine learning models, and based on the sporting recommendation and a predicted hunting license utilization rate, a quantity of hunting licenses to be issued, wherein the predicted hunting license utilization rate is based on historical sportsmen success rates and harvest compliance metrics stored in the one or more sportsmen profiles;

compile, by the one or more machine learning models, based on the one or more sportsmen profiles, a prioritized list of the one or more sportsmen profiles to be allocated the quantity of hunting licenses wherein the prioritized list is determined based on at least one of license history data, sporting history data, and conservation history data or donation history data;

issue, based on the prioritized list, by a computing device in communication with the artificial neural network, the quantity of hunting licenses via one or more printable or digitally distributable license documents;

receive, by the computing device, post-issuance harvest data from one or more sportsmen of the prioritized list, wherein the post-issuance harvest data indicates whether animals of the species were successfully harvested using the issued quantity of hunting licenses; and

retrain, by the training model of the one or more machine learning models, the predictive population model using the post-issuance harvest data to improve a predictive accuracy of the predictive population model for a subsequent issuance of hunting licenses.

16 . The one or more non-transitory computer readable media of claim 15 , wherein the processor-executable instructions that, when executed by the at least one processor, cause the at least one processor to issue, based on the prioritized list, the quantity of hunting licenses further cause the at least one processor to cause paper documentation to be sent to one or more addresses associated with the one or more sportsmen profiles.

17 . The one or more non-transitory computer readable media of claim 15 , wherein the one or more sportsmen profiles comprise data associated a respective sportsman comprising at least one of demographic information, previous sporting information, donation information, or conservation information.

18 . The one or more non-transitory computer readable media of claim 15 , wherein the prioritized list of the one or more sportsmen profiles indicates a probability for each sportsman of a plurality of sportsmen to receive a hunting license of the quantity of hunting licenses.

19 . The one or more non-transitory computer readable media of claim 15 , wherein the prioritized list of the one or more sportsmen profiles comprises one or more priority tiers that are associated with a probability of each sportsman associated with a respective priority tier to be issued a hunting license.

20 . The one or more non-transitory computer readable media of claim 15 , wherein the processor-executable instructions, when executed by the at least one processor, further cause the at least one processor to determine the habitat data and the wildlife data, wherein the habitat data indicates a health of a habitat associated with the species, and wherein the wildlife data indicates one or more of: a current population of the species, the predicted population of the species, and/or a sustainable population of the species.

21 . The one or more non-transitory computer readable media of claim 15 , wherein each section of the plurality of sections is defined based on at least one of a topography of the habitat zone, a natural habitat of the species, landmarks, natural boundaries, or manmade boundaries.