Fuel leak determination via predictive modeling
Data characterizing a fuel storage facility can be received from one or more of a plurality of sensors disposed in the fuel storage facility. A fuel leak prediction for the fuel storage facility can be determined by a server, based on the received data, and further based on at least one predictive model that predicts whether a fuel leak exists in the fuel storage facility. The fuel leak prediction can be provided by the server. Related apparatus, systems, methods, techniques, and articles are also described.
1. A method comprising:
receiving, from one or more of a plurality of sensors disposed in a fuel storage facility, data characterizing the fuel storage facility;
determining, by a server and based on the received data, a predicted fuel leakage rate for the fuel storage facility, the determining further based on at least one predictive model that predicts whether a fuel leak exists in the fuel storage facility, the at least one predictive model being based on one or more user-provided parameters;
providing a visual characterization of the predicted fuel leakage rate for the fuel storage facility to a display communicatively coupled to the server;
wherein the one or more user-provided parameters include at least one of a time period of operation of the fuel storage facility and at least one data quality parameter to improve a quality of the received data.
2. The method of claim 1 , wherein the time period of operation is at least one period of 30 days.
3. The method of claim 1 , wherein the time period of operation is at least 60 days including a first period and a second period each being at least 30 days, and wherein the data characterizing the fuel storage facility includes a first data set from the first period and a second data set from the second period.
4. The method of claim 3 , wherein the determined predicted fuel leakage rate comprises a first predicted fuel leakage rate corresponding to the first data set from the first period and a second predicted fuel leakage rate corresponding to the second data set from the second period.
5. The method of 4 further comprising determining a combined predicted fuel leakage rate based on a difference between the first predicted fuel leakage rate and the second predicted fuel leakage rate.
6. The method of claim 1 , wherein the at least one period of time comprises a first period of time and a second period of time, the first and second periods of time having different lengths.
7. The method of claim 1 , wherein the at least one period of time comprises a first period of time and a second period of time, the first and second periods of time being non-contiguous.
8. The method of claim 1 , wherein the at least one period of time comprises a first period of time and a second period of time, the second period of time being offset from the first period of time by one year.
9. The method of claim 1 , wherein the at least one data quality parameter includes an indication to ignore or remove portions of the data if the predicted fuel leakage rate exceeds a predetermined value.
10. The method of claim 1 , wherein the at least one data quality parameter includes an artificially-induced leakage parameter corresponding to an accuracy benchmark against the predicted fuel leakage rate.
11. The method of claim 10 , wherein the at least one data quality parameter includes a parameter for a threshold on leakage recovered.
12. The method of claim 11 , wherein the threshold on leakage recovered is equal to approximately 85-90% of the artificially-induced leakage parameter.
13. A system comprising:
at least one data processor; and
memory storing instructions configured to cause the at least one data processor to perform operations comprising:
receive, from one or more of a plurality of sensors disposed in a fuel storage facility, data characterizing the fuel storage facility;
determine, by a server and based on the received data, a predicted fuel leakage rate for the fuel storage facility, the determining further based on at least one predictive model that predicts whether a fuel leak exists in the fuel storage facility, the at least one predictive model being based on one or more user-provided parameters;
provide a visual characterization of the predicted fuel leakage rate for the fuel storage facility to a display communicatively coupled to the server;
wherein the one or more user-provided parameters include at least one of a time period of operation of the fuel storage facility and at least one data quality parameter to improve a quality of the received data.
14. The system of claim 13 , wherein the time period of operation is at least one period of 30 days.
15. The system of claim 13 , wherein the time period of operation is at least 60 days including a first period and a second period each being at least 30 days, and wherein the data characterizing the fuel storage facility includes a first data set from the first period and a second data set from the second period.
16. The system of claim 15 , wherein the determined predicted fuel leakage rate comprises a first predicted fuel leakage rate corresponding to the first data set from the first period and a second predicted fuel leakage rate corresponding to the second data set from the second period.
17. The system of 16 further comprising determining a combined predicted fuel leakage rate based on a difference between the first predicted fuel leakage rate and the second predicted fuel leakage rate.
18. The system of claim 13 , wherein the at least one period of time comprises a first period of time and a second period of time, the first and second periods of time having different lengths.
19. The system of claim 13 , wherein the at least one period of time comprises a first period of time and a second period of time, the first and second periods of time being non-contiguous.
20. The system of claim 13 , wherein the at least one period of time comprises a first period of time and a second period of time, the second period of time being offset from the first period of time by one year.
21. The system of claim 13 , wherein the at least one data quality parameter includes an indication to ignore or remove portions of the data if the predicted fuel leakage rate exceeds a predetermined value.
22. The system of claim 13 , wherein the at least one data quality parameter includes an artificially-induced leakage parameter corresponding to an accuracy benchmark against the predicted fuel leakage rate.
23. The system of claim 22 , wherein the at least one data quality parameter includes a parameter for a threshold on leakage recovered.
24. The system of claim 23 , wherein the threshold on leakage recovered is equal to approximately 85-90% of the artificially-induced leakage parameter.
25. A non-transitory computer program product storing instructions which, when executed by at least one data processor forming part of at least one computing system, cause the at least one data processor to implement operations comprising:
receive, from one or more of a plurality of sensors disposed in a fuel storage facility, data characterizing the fuel storage facility;
determine, by a server and based on the received data, a predicted fuel leakage rate for the fuel storage facility, the determining further based on at least one predictive model that predicts whether a fuel leak exists in the fuel storage facility, the at least one predictive model being based on one or more user-provided parameters;
provide a visual characterization of the predicted fuel leakage rate for the fuel storage facility to a display communicatively coupled to the server;
wherein the one or more user-provided parameters include at least one of a time period of operation of the fuel storage facility and at least one data quality parameter to improve a quality of the received data.