System and method for managing water
A device includes an image data receiving component, a vegetation index generation component, a GLC matrix component, a plurality of classifying components and a voting component. The image data receiving component receives multiband image data of a geographic region. The vegetation index generation component generates a normalized difference vegetation index based on the received multiband image data. The GLC matrix component generates a grey level co-occurrence matrix image band based on the received multiband image data. The classifying components generate land cover classifications based on the received multiband image data, the normalized difference vegetation index and the grey level co-occurrence matrix image band. The voting component generates a final land cover classification based a majority vote of the land cover classifications.
1. A device comprising at least one non-transitory computer-readable media storing a set of instructions for running on a computer system, that when executed cause the computer system to:
an image data receiving component operable to receive multiband image data of an image of a geographic region;
a vegetation index generation component operable to generate a normalized difference vegetation index based on the received multiband image data of the image;
a grey level co-occurrence matrix generation component operable to generate a grey level co-occurrence matrix image band based on the received multiband image data of the image;
a first classification component operable generate a first land cover classification based on the received multiband image data of the image, the normalized difference vegetation index and the grey level co-occurrence matrix image band;
a second classification component operable generate a second land cover classification based on the received multiband image data of the image, the normalized difference vegetation index and the grey level co-occurrence matrix image band;
a third classification component operable generate a third land cover classification based on the received multiband image data of the image, the normalized difference vegetation index and the grey level co-occurrence matrix image band; and
a voting component operable to generate a final land cover classification based on a majority vote of the first land cover classification, the second land cover classification and the third land cover classification;
generate a model based on the final land cover classification of the geographic region, by:
extrapolating a first predicted water usage forecast for the geographic region based at least on the final land cover classification of the geographic region, a water budget, and a difference of an amount of water between the water budget and one or more water meter readings of the geographic region;
iteratively extrapolating a second predicted water usage forecast for the geographic region based at least on the final land cover classification, the water budget, and a difference of an amount of water between the water budget and one or more current water readings for the geographic region; and
deriving a relationship between the final land cover classification and water use, without using the water budget; and
predict a third predicted water usage forecast based on the generated model.
2. The device of claim 1 , wherein said image data receiving component is operable to the at least one non-transitory computer-readable media storing a set of instructions for running on a computer system, that when executed further cause the computer system to:
receive the multiband image data of the image of a the geographic region as an RGB and near infra-red image data of the geographic region.
3. The device of claim 2 ,
wherein the multiband image data of the image corresponds to an array of pixels of the image, and
wherein said first classification component is operable to the at least one non-transitory computer-readable media storing the set of instructions for running on the computer system, that when executed further cause the computer system to:
generate the first land cover classification by classifying each of the pixels of the multiband image data of the image as one of the group consisting of grass, a tree, a shrub, a man-made surface, a man-made pool, a natural water body and artificial turf.
4. The device of claim 3 , wherein said first classification component generating the first land cover classification based on the received multiband image data of the image, the normalized difference vegetation index and the grey level co-occurrence matrix image band, further comprises utilizing one of the group consisting of a simple classification and regression tree classifier, a naïve Bayes classifier, a random forecasts classifier, a GMO max entropy classifier, an MCP classifier, a Pegasos classifier, an ICPamir classifier, a voting SVM classifier, a margin SVM classifier and a Winnow classifier.
5. The device of claim 4 1 , further comprising a parcel data receiving component operable to wherein the at least one non-transitory computer-readable media storing the set of instructions for running on the computer system, that when executed further cause the computer system to:
receive parcel data.
6. The device of claim 1 ,
wherein the multiband image data of the image corresponds to an array of pixels, and
wherein said first classification component operable the at least one non-transitory computer-readable media storing the set of instructions for running on the computer system, that when executed further cause the computer system to:
generate the first land cover classification by classifying each of pixels of the multiband image data of the image as one of the group consisting of grass, a tree, a shrub, a man-made surface, a man-made pool, a natural water body and artificial turf.
7. The device of claim 1 , wherein said first classification component comprises generating the first land cover classification based on the received multiband image data of the image, the normalized difference vegetation index and the grey level co-occurrence matrix image band, further comprises utilizing one of the group consisting of a simple classification and regression tree classifier, a naïve Bayes classifier, a random forecasts classifier, a GMO max entropy classifier, a MCP classifier a, a Pegasos classifier, an ICPamir classifier, a voting SVM classifier, a margin SVM classifier and a Winnow classifier.
8. The device of claim 1 , further comprising a regression component operable to extrapolate a predicted water usage based on a history of water usage.
9. A method, comprising:
receiving, via an image data receiving component, multiband image data of an image of a geographic region;
generating, via a vegetation index generation component, a normalized difference vegetation index based on the received multiband image data of the image;
generating, via a grey level co-occurrence matrix generation component, a grey level co-occurrence matrix based on the received multiband image data of the image;
generating, via a first classification component, a first land cover classification based on the received multiband image data of the image, the normalized difference vegetation index and the grey level co-occurrence matrix;
generating, via a second classification component, a second land cover classification based on the received multiband image data of the image, the normalized difference vegetation index and the grey level co-occurrence matrix;
generating, via a third classification component, a third land cover classification based on the received multiband image data of the image, the normalized difference vegetation index and the grey level co-occurrence matrix;
generating, via a voting component, a final land cover classification based on a majority vote of the first land cover classification, the second land cover classification and the third land cover classification;
generating a model based on the final land cover classification of the geographic region, by:
extrapolating a first predicted water usage forecast for the geographic region based at least on the final land cover classification of the geographic region, a water budget, and a difference of an amount of water between the water budget and one or more water meter readings for the geographic region;
iteratively extrapolating a second predicted water usage forecast for the geographic region based at least on the final land cover classification, the water budget, and a difference of an amount of water between the water budget and one or more current water meter readings for the geographic region; and
deriving a relationship between the final land cover classification and water use, without using the water budget; and
predicting a third predicted water usage forecast based on the generated model.
10. The method of claim 9 , wherein said receiving multiband image data of the image of a the geographic region further comprises:
receiving the multiband image data of the image of a the geographic region as an RGB and near infra-red image data of the geographic region.
11. The method of claim 10 , wherein the multiband image data of the image corresponds to an array of pixels, and wherein said generating a first land cover classification further comprises:
generating the first land cover classification by classifying each of pixels of the multiband image data of the image as one of the group consisting of grass, a tree, a shrub, a man-made surface, a man-made pool, a natural water body and artificial turf.
12. The method of claim 11 , wherein said generating a first land cover classification, further comprises:
generating comprises generating via one of the group consisting of a simple classification and regression tree classifier, a naïve Bayes classifier, a random forecasts classifier, a GMO max entropy classifier, an MCP classifier, a Pegasos classifier, an ICPamir classifier, a voting SVM classifier, a margin SVM classifier and a Winnow classifier.
13. The method of claim 12 9 , further comprising:
receiving, via a parcel data receiving component, parcel data.
14. The method of claim 9 , wherein the multiband image data of the image corresponds to an array of pixels, and wherein said generating a first land cover classification further comprises:
generating the first land cover classification by classifying each of pixels of the multiband image data of the image as one of the group consisting of grass, a tree, a shrub, a man-made surface, a man-made pool, a natural water body and artificial turf.
15. The method of claim 9 , wherein said generating a first land cover classification further comprises:
generating comprises generating via one of the group consisting of a simple classification and regression tree classifier, a naïve Bayes classifier, a random forecasts classifier, a GMO max entropy classifier, an MCP classifier, a Pegasos classifier, an ICPamir classifier, a voting SVM classifier, a margin SVM classifier and a Winnow classifier.
16. The method of claim 9 , further comprising extrapolating, via a regression component, a predicted water usage based on a history of water usage.
17. A One or more non-transitory, tangible, computer-readable media having computer-readable instructions stored thereon, for use with a computer and being capable of instructing the computer to perform the method comprising:
receiving, via an image data receiving component, multiband image data of an image of a geographic region;
generating, via a vegetation index generation component, a normalized difference vegetation index based on the received multiband image data of the image;
generating, via a grey level co-occurrence matrix generation component, a grey level co-occurrence matrix based on the received multiband image data of the image;
generating, via a first classification component, a first land cover classification based on the received multiband image data of the image, the normalized difference vegetation index and the grey level co-occurrence matrix;
generating, via a second classification component, a second land cover classification based on the received multiband image data of the image, the normalized difference vegetation index and the grey level co-occurrence matrix;
generating, via a third classification component, a third land cover classification based on the received multiband image data of the image, the normalized difference vegetation index and the grey level co-occurrence matrix; and
generating, via a voting component, a final land cover classification based on a majority vote of the first land cover classification, the second land cover classification and the third land cover classification;
generating a model based on the final land cover classification of the geographic region, by:
extrapolating a first predicted water usage forecast for the geographic region based at least on the final land cover classification of the geographic region, a water budget, and a difference of an amount of water between the water budget and one or more water meter readings for the geographic region;
iteratively extrapolating a second predicted water usage forecast for the geographic region based on at least the final land cover classification, the water budget, and a difference of an amount of water between the water budget and one or more current water meter readings for the geographic region;
deriving a relationship between the final land cover classification and water use, without using the water budget; and
predicting a third predicted water usage forecast based on the generated model.
18. The one or more non-transitory, tangible computer-readable media of claim 17 , wherein the computer-readable instructions are capable of instructing the computer to perform the method such that said receiving multiband image data of the image of a the geographic region comprises receiving the multiband image data of the image of a the geographic region as an RGB and near infra-red image data of the image of the geographic region.
19. The one or more non-transitory, tangible, computer-readable media of claim 18 , wherein the multiband image data of the image corresponds to an array of pixels, and wherein said generating a first land cover classification further comprises:
generating the first land cover classification by classifying each of pixels of the multiband image data of the image as one of the group consisting of grass, a tree, a shrub, a man-made surface, a man-made pool, a natural water body and artificial turf.
20. The one or more non-transitory, tangible, computer-readable media of claim 19 , wherein the computer-readable instructions are capable of instructing the computer to perform the method such that said generating a first land cover classification further comprises generating comprises generating via one of the group consisting of a simple classification and regression tree classifier, a naïve Bayes classifier, a random forecasts classifier, a GMO max entropy classifier, an MCP classifier, a Pegasos classifier, an ICPamir classifier, a voting SVM classifier, a margin SVM classifier and a Winnow classifier.
21. The device of claim 5 , wherein the geographic region is determined based on the parcel data.
22. A system comprising at least one non-transitory computer-readable media storing instructions for running on a computer, that when executed cause the computer to:
receive multiband image data of an image of a geographic region of interest for water management, the multiband image data of the image comprising pixels;
classify one or more of the pixels of the multiband image data of the image as one of a group of predetermined land covers by:
generating, for each of the pixels of the one or more pixels, a plurality of land cover classifications; and
determining, for each of the pixels of the one or more pixels, a final land cover classification from the plurality of land cover classifications;
generate a model based on the final land cover classification of the geographic region, by:
extrapolating a predicted water usage forecast for the geographic region based at least on the final land cover classification of the geographic region, a water budget, and a difference of an amount of water between the water budget and one or more water meter readings for the geographic region;
iteratively extrapolating a second predicted water usage forecast for the geographic region based at least on the final land cover classification, the water budget, and a difference of an amount of water between the water budget and one or more current water meter readings for the geographic region;
deriving a relationship between the final land cover classification and water use, without using the water budget; and
predict a third predicted water usage forecast based on the generated model.
23. The system of claim 22 , wherein determining, for each of the pixels of the one or more pixels, the final land cover classification from the plurality of land cover classifications is based on a majority vote of the plurality of land cover classifications.
24. The system of claim 22 , wherein determining, for each of the pixels of the one or more pixels, the final land cover classification from the plurality of land cover classifications, further comprises:
receiving image training data indicative of an analysis of imagery depicting vegetation and one or more man-made surface.
25. The system of claim 22 , wherein classifying one or more of the pixels of the multiband image data of the image as one of the group of predetermined land covers, further comprises:
utilizing image training data indicative of an analysis of imagery depicting vegetation or one or more man-made surface.
26. The method of claim 22 , wherein iteratively extrapolating, with the system, a second predicted water usage forecast is further based on one or more of: demographic data, economic data, and parcel information;
wherein the parcel information comprises one or more of: an area of the geographic region, an area of a dwelling located within the geographic region, and number of bathrooms located within the dwelling.
27. A method, comprising:
receiving, with one or more computers, multiband image data of an image of a geographic region, the multiband image data of the image having pixels;
receiving, with the one or more computers, image training data indicative of an analysis of imagery depicting vegetation and one or more man-made surface;
classifying, with the one or more computers, one or more of the pixels of the multiband image data of the image as one of a group of predetermined land covers by:
generating, with the one or more computers, a plurality of land cover classifications, for each of the pixels of the one or more pixels, based on analyzing the received multiband image data of the image with the image training data; and
generating, with the one or more computers, a final land cover classification for the geographic region based on the plurality of land cover classifications;
generating a model based on the final land cover classification of the geographic region, by:
extrapolating, with the one or more computers, a first predicted water usage forecast for the geographic region based at least on the final land cover classification, a water budget, and a difference of an amount of water between the water budget and one or more water meter readings for the geographic region;
iteratively extrapolating, with the one or more computers, a second predicted water usage forecast for the geographic region based at least on the final land cover classification, the water budget, and a difference of an amount of water between the water budget and one or more current water meter readings for the geographic region;
deriving, with the one or more computers, a relationship between the final land cover classification and water use, without using the water budget; and
predicting, with the one or more computers, a third predicted water usage forecast based on the generated model.
28. The method of claim 27 , wherein generating, with the one or more computers, the final land cover classification is based on a majority vote of the plurality of land cover classifications.
29. The method of claim 27 , wherein iteratively extrapolating, with the one or more computers, the second predicted water usage forecast is further based on one or more of: demographic data, economic data, and parcel information;
wherein the parcel information comprises one or more of: an area of the geographic region, an area of a dwelling located within the geographic region, and number of bathrooms located within the dwelling located within the geographic region.