Dynamic water quality prediction

Patent metadata

Field	Value
Publication number	US-2017276660-A1
Application number	US-201615077363-A
Country	US
Kind code	A1
Filing date	Mar 22, 2016
Priority date	Mar 22, 2016
Publication date	Sep 28, 2017
Grant date	—

Abstract

Technical solutions are described for predicting water quality of a water source over a forecast horizon and for multiple locations. An example computer-implemented method includes receiving a forecast horizon for across which to predict the water quality. The forecast horizon includes a plurality of time periods. The computer-implemented method also includes receiving one or more geographical locations at which to predict the water quality. The computer-implemented method also includes receiving a set of water quality measures for the water source. The computer-implemented method also includes determining predicted water quality measures for the geographical location at each of the plurality of time periods in the forecast horizon based on the water quality measures. The computer-implemented method also includes outputting one or more of the predicted water quality measures.

First claim

What is claimed is:

1 . A computer implemented method for predicting water quality of a water source, the method comprising:
receiving a forecast horizon for across which to predict the water quality, wherein the forecast horizon comprises a plurality of time periods; receiving one or more geographical locations at which to predict the water quality; receiving a set of water quality measures for the water source; determining predicted water quality measures for the geographical locations at each of the plurality of time periods in the forecast horizon based on the water quality measures; and outputting one or more of the predicted water quality measures.

2 . The computer implemented method of claim 1 , wherein the set of water quality measures is received from a geographical location that is upstream from the geographical location at which the water quality is predicted.

3 . The computer implemented method of claim 1 , wherein the water quality measure comprises dissolved oxygen, turbidity, and a combination thereof.

4 . The computer implemented method of claim 1 , wherein the predicted water quality measures are determined based on a Bayesian network.

5 . The computer implemented method of claim 1 , wherein the predicted water quality measures are determined further based on historical water quality measures at the geographical locations.

6 . The computer implemented method of claim 1 , wherein the predicted water quality measures are determined further based on satellite images of the water source.

7 . The computer implemented method of claim 1 , further comprising:
transmitting an alert in response to a predicted water quality measure from the predicted water quality measures being indicative of contamination above a predetermined threshold.

8 . The computer implemented method of claim 7 , further comprising:
transmitting an explanation of the predicted water quality measure being indicative of the contamination above the predetermined threshold.

9 . A system for predicting water quality of a water source, the system comprising:
a memory; and a processor configured to:
receive a forecast horizon for across which to predict the water quality, wherein the forecast horizon comprises a plurality of time periods;
receive a one or more geographical locations at which to predict the water quality;
receive a set of water quality measures for the water source;
determine predicted water quality measures for the geographical locations at each of the plurality of time periods in the forecast horizon based on the water quality measures; and
output one or more of the predicted water quality measures.

10 . The system of claim 9 , wherein the set of water quality measures is received from a geographical location that is upstream from the geographical locations at which the water quality is predicted.

11 . The system of claim 9 , wherein the water quality measure comprises dissolved oxygen, turbidity, and a combination thereof.

12 . The system of claim 9 , wherein the predicted water quality measures are determined based on images of the water source uploaded on a social media data repository.

13 . The system of claim 9 , wherein the predicted water quality measures are determined further based on historical water quality measures at the geographical locations.

14 . The system of claim 9 , wherein the processor is further configured to:
transmit an alert in response to a predicted water quality measure from the predicted water quality measures being indicative of contamination above a predetermined threshold.

15 . The system of claim 14 , wherein the processor is further configured to:
transmit an explanation of the predicted water quality measure being indicative of the contamination above the predetermined threshold.

16 . A computer program product for predicting water quality of a water source, the computer program product comprising a computer readable storage medium, the computer readable storage medium comprising computer executable instructions, wherein the computer readable storage medium comprises instructions to:
receive a forecast horizon for across which to predict the water quality, wherein the forecast horizon comprises a plurality of time periods; receive one or more geographical locations at which to predict the water quality; receive a set of water quality measures for the water source; determine predicted water quality measures for the geographical locations at each of the plurality of time periods in the forecast horizon based on the water quality measures; and output one or more of the predicted water quality measures.

17 . The computer program product of claim 16 , wherein the predicted water quality measures are determined based on images of the water source uploaded on a social media data repository.

18 . The computer program product of claim 16 , wherein the predicted water quality measures are determined based on images of the water source uploaded on a social media data repository.

19 . The computer program product of claim 16 , wherein the predicted water quality measures are determined further based on historical water quality measures at the geographical locations.

20 . The computer program product of claim 16 , wherein the computer readable storage medium comprises instructions to:
transmit an alert in response to a predicted water quality measure from the predicted water quality measures being indicative of contamination above a predetermined threshold.

Assignees

• IBM

Inventors

• Ba Amadou
• Marinescu Radu
• Mckenna Sean A

Classifications

• G01N33/1826 Primary

  Organic contamination in water · CPC title

• G06Q10/04

  Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202) · CPC title

• G06Q50/06

  Energy or water supply · CPC title

• Y02A20/152

  Water filtration · CPC title