Claims:1. A method of predicting occurrence of one or more natural disasters for preventing data loss and infrastructure outage, said method comprising processor implemented steps of:

receiving data pertaining to said one or more natural disasters from a plurality of data sources using a data reception module (202);
processing said received data to extract one or more parameters related to said one or more natural disasters using a data processing module (204);
analysing said extracted one or more parameters to predict the occurrence of said one or more natural disasters using a data analysis and prediction module (206); and
preventing data loss and infrastructure outage based on the predicted occurrence of said one or more natural disasters using a data loss prevention module (208).

2. The method as claimed in claim 1, wherein said one or more natural disasters are selected from a group comprising of geological disasters, hydrological disasters and meteorological disasters.

3. The method as claimed in claim 2, wherein said geological disasters are earthquakes.

4. The method as claimed in claim 2, wherein said hydrological disasters are selected from a group comprising of flood and tsunami.

5. The method as claimed in claim 2, wherein said meteorological disasters are selected from a group comprising of storm and tornado.

6. The method as claimed in claim 1, wherein said plurality of data sources comprises of a historical data repository (302), a real time data repository (304) and a predicted data repository (306) pertaining to said one or more natural disasters.

7. The method as claimed in claim 1, wherein receiving of data pertaining to one or more natural disasters from the plurality of data sources further comprises of:

a. extracting real time data pertaining to said one or more natural disasters from the real time data repository (304) using a web analytics engine (308), wherein said web analytics engine (308) is communicatively coupled with the real time data repository (304) over a commination network; and
b. extracting predicted data pertaining to said one or more natural disasters from the predicted data repository (306) using a predictive analytics engine (310), wherein said predictive analytics engine ( 310) is communicatively coupled with the real predicted data repository (306) over a commination network.

8. The method as claimed in Claim 7 further comprises of performing web crawling using a web crawling module (402), web mining using a web mining module (404) and web analysis using a web analysis module (406) while extracting real time data pertaining to said one or more natural disasters from the real time data repository (304).

9. The method as claimed in Claim 1, wherein said extracted one or more parameters for earthquake are selected from earthquakes of 4.0 magnitude and above on Richter scale.

10. The method as claimed in Claim 1, wherein said extracted one or more parameters for storm and tornado are selected from a group comprising of severity and category of storm and tornado.

11. The method as claimed in Claim 1, wherein said extracted one or more parameters for flood are selected from a group comprising temperature, humidity, wind speed, wind degree, dew point, visibility, gust speed, sea level pressure, precipitation and events.

12. The method as claimed in claim 1, wherein said extracted one or more parameters are analysed to determine if said extracted one or more parameters cross a user defined threshold set for each of said one or more natural disasters in case of said occurrence of natural disasters.

13. The method as claimed in Claim 1, wherein the data loss is prevented by using the data loss prevention module (208) by selecting at least one option from a group comprising of data migration, data backup, data replication and data transfer.

14. The method as claimed in Claim 13, wherein data migration is attained by migrating data from one or more source data center to one or more destination data center.

15. The method as claimed in claim 14, wherein said one or more source data center is predicted to be struck with said one or more natural disasters and said one or more destination data center is outside the purview of predicted said one or more natural disasters.

16. A system of predicting occurrence of one or more natural disasters for preventing data loss and infrastructure outage, said system comprising:

a processor;
a data bus coupled to said processor; and
a computer-usable medium embodying computer code, said computer-usable medium being coupled to said data bus, said computer program code comprising instructions executable by said processor and configured for operating:

a. a data reception module (202) adapted for receiving data pertaining to one or more natural disasters from a plurality of data sources;
b. a data processing module (204) adapted for processing said received data to extract one or more parameters related to said one or more natural disasters (204);
c. a data analysis and prediction module (206) adapted for analysing said extracted one or more parameters to predict the occurrence of said one or more natural disasters;
d. a data loss prevention module (208) adapted for preventing data loss and infrastructure outage based on the predicted occurrence of said one or more natural disasters.

a plurality of data sources containing data pertaining to said one or more natural disasters, wherein said plurality of data sources comprises of a historical data repository (302), a real time data repository (304) and a predicted data repository (306).

17. The system as claimed in claim 16, wherein said data reception module (202) further comprises of

a. a web analytics engine (308) communicatively coupled with the real time data repository (304) over a commination network and adapted for extracting real time data pertaining to said one or more natural disasters from the real time data repository (304); and
b. a predictive analytics engine (310) communicatively coupled with the real predicted data repository (306) over a commination network and adapted for extracting predicted data pertaining to said one or more natural disasters from the predicted data repository (306).

18. The system as claimed in Claim 17, wherein the web analytics engine further comprises of a web crawling module (402) adapted for web crawling, a web mining module (404) adapted for web mining and a web analysis module (406) adapted for web analysis while extracting real time data pertaining to said one or more natural disasters from the real time data repository (304).
, Description:FORM 2
THE PATENTS ACT, 1970
(39 of 1970)

THE PATENT RULES, 2003

COMPLETE SPECIFICATION

(See Section 10 and Rule 13)

Title of invention:

A METHOD AND SYSTEM OF PREDICTING NATURAL DISASTERS FOR PREVENTING DATA LOSS AND INFRASTRUCTURE OUTAGE

Applicant:
Tata Consultancy Services Limited
A company Incorporated in India under the Companies Act, 1956
Having address:
Nirmal Building, 9th floor,
Nariman point, Mumbai 400021,
Maharashtra, India

The following specification particularly describes the invention and the manner in which it is to be performed.

FIELD OF THE INVENTION

[001] The present application generally relates to prevention of data loss and infrastructure outage. More particularly, the invention provides a method and system for predicting the occurrence of natural disasters at user specified locations for preventing data loss and infrastructure outage.

BACKGROUND OF THE INVENTION

[002] Data stored in data centers is critical for all stakeholders of an organization. At the same time, infrastructure service outage or data loss downtime is inevitable and a single downtime might result in disastrous circumstances for the business. Each data center or infrastructure outage can be broadly categorized as either planned or unplanned. A planned network outage occurs when an application or hardware element is taken out of service for maintenance or upgrades, whereas an unplanned outage can be caused by hardware faults, human errors, equipment failure such as disk crash, disruption of power supply, application failure or corruption of database, human error, sabotage or strike, malicious software, virus attacks, hacking or other internet attacks, natural disasters and so on.

[003] With the advancement in technologies and business continuity planning, there are many workaround available to deal with both planned and unplanned outages. However, despite decades of innovation, many organizations still do not take natural disasters into account while designing the disaster recovery or business continuity plan. According to various reports, very limited number of organizations can tolerate less than an hour of downtime before they experience a significant loss in revenue or business impact. Overall, approximately 12-18% of the outages are due to natural disaster related events. As a result, a system which can predict the occurrence of natural disasters to prevent data loss and infrastructure outage by means of providing options such as data transfer, data backup, data migration and data replication is very necessary in today’s scenario.

[004] Existing prior art illustrates prediction systems for certain individual natural disasters which provide warnings and alerts about the occurrence of natural disasters with varied accuracy. The systems are neither comprehensive enough to predict a considerable number of natural disasters and nor do they provide any kind of suggestion or option about what needs to be done to ensure data safety in case the predicted natural disaster takes place in a specific location. .

[005] Further, prior art also provides for methods and systems of using social networks and crowd-sourcing to give warnings and alerts about natural disasters, but they do not provide for any robust prediction system about a considerable number of natural disaster and neither do they provide any recommendation for preventing data loss and service outage.

[006] Thereby, accurate prediction about the occurrence of natural disasters, providing alerts about the occurrence of the same and suggesting viable recommendations to prevent data loss and infrastructure outage is still considered as one of the biggest challenges of the technical domain.

OBJECTIVE OF THE INVENTION

[007] In accordance with the present invention, an objective is to provide a system and method to predict the occurrence of natural disasters for prevention of data loss and infrastructure outage.

[008] Another objective of the invention is to provide for a complete recommendation system for prevention of data loss and infrastructure outage for organizations.

[009] Another objective of the invention is to sense and monitor climatic conditions in specific locations where an organization’s data center is located.

[010] Another objective of the invention is to provide real time alerts for the occurrence of natural disasters for prevention of data loss and infrastructure outage.

[011] Yet another objective of the invention is to act as a comprehensive system to aid in an organization’s business continuity planning.

SUMMARY OF THE INVENTION

[012] Before the present methods, systems, and hardware enablement are described, it is to be understood that this invention is not limited to the particular systems, and methodologies described, as there can be multiple possible embodiments of the present invention which are not expressly illustrated in the present disclosure. It is also to be understood that the terminology used in the description is for the purpose of describing the particular versions or embodiments only, and is not intended to limit the scope of the present invention which will be limited only by the appended claims.

[013] The present disclosure envisages a method and system which can prevent data loss and infrastructure outage caused by natural disasters by designing a location based natural disaster alert mechanism by predicting one or more natural disasters by extracting natural disaster alert data from web.

[014] In an embodiment of the invention, a method for predicting occurrence of one or more natural disasters for preventing data loss and infrastructure outage is provided. The method comprises processor implemented steps of receiving data pertaining to said one or more natural disasters from a plurality of data sources using data reception module (202), processing said received data to extract one or more parameters related to said one or more natural disasters using data processing module (204), analysing said extracted one or more parameters to predict the occurrence of said one or more natural disasters using data analysis and prediction module (206) and preventing data loss and infrastructure outage based on the predicted occurrence of said one or more natural disasters using data loss prevention module (208).

[015] In another embodiment of the invention, a system for predicting occurrence of one or more natural disasters for preventing data loss and infrastructure outage is provided. The system comprises of a processor, a data bus coupled to the processor, a computer-usable medium embodying computer code and a plurality of data sources containing data pertaining to the one or more natural disasters, wherein said plurality of data sources comprises of a historical data repository (302), a real time data repository (304) and a predicted data repository (306). The computer-usable medium is coupled to the data bus and the computer program code comprising instructions executable by said processor and configured for operating a data reception module (202) adapted for receiving data pertaining to one or more natural disasters from a plurality of data sources, a data processing module (204) adapted for processing said received data to extract one or more parameters related to said one or more natural disasters (204), a data analysis and prediction module (206) adapted for analysing said extracted one or more parameters to predict the occurrence of said one or more natural disasters and a data loss prevention module (208) adapted for preventing data loss and infrastructure outage based on the predicted occurrence of said one or more natural disasters.

BRIEF DESCRIPTION OF THE DRAWINGS

[016] The foregoing summary, as well as the following detailed description of preferred embodiments, are better understood when read in conjunction with the appended drawings. For the purpose of illustrating the invention, there is shown in the drawings exemplary constructions of the invention; however, the invention is not limited to the specific methods and system disclosed. In the drawings:

[017] Figure 1 shows a flow chart illustrating method for predicting occurrence of one or more natural disasters for preventing data loss and infrastructure outage;

[018] Fig. 2 shows a block diagram of a system for predicting occurrence of one or more natural disasters for preventing data loss and infrastructure outage;

[019] Fig. 3 shows a block diagram of the data processing module; and

[020] Fig. 4 shows a block diagram of the web analytics engine.

DETAILED DESCRIPTION OF THE INVENTION

[021] Some embodiments of this invention, illustrating all its features, will now be discussed in detail.

[022] The words "comprising," "having," "containing," and "including," and other forms thereof, are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items.

[023] It must also be noted that as used herein and in the appended claims, the singular forms "a," "an," and "the" include plural references unless the context clearly dictates otherwise. Although any systems and methods similar or equivalent to those described herein can be used in the practice or testing of embodiments of the present invention, the preferred, systems and methods are now described. In the following description for the purpose of explanation and understanding reference has been made to numerous embodiments for which the intent is not to limit the scope of the invention.

[024] One or more components of the invention are described as module for the understanding of the specification. For example, a module may include self-contained component in a hardware circuit comprising of logical gate, semiconductor device, integrated circuits or any other discrete component. The module may also be a part of any software programme executed by any hardware entity for example processor. The implementation of module as a software programme may include a set of logical instructions to be executed by a processor or any other hardware entity.

[025] The disclosed embodiments are merely exemplary of the invention, which may be embodied in various forms.

[026] The elements illustrated in the Figures interoperate as explained in more detail below. Before setting forth the detailed explanation, however, it is noted that all of the discussion below, regardless of the particular implementation being described, is exemplary in nature, rather than limiting. For example, although selected aspects, features, or components of the implementations are depicted as being stored in memories, all or part of the systems and methods consistent with the natural disaster prediction system and method may be stored on, distributed across, or read from other machine-readable media.

[027] Method steps of the invention may be performed by one or more computer processors executing a program tangibly embodied on a computer-readable medium to perform functions of the invention by operating on input and generating output. Suitable processors include, by way of example, both general and special purpose microprocessors. Generally, the processor receives (reads) instructions and data from a memory (such as a read-only memory and/or a random access memory) and writes (stores) instructions and data to the memory. Storage devices suitable for tangibly embodying computer program instructions and data include, for example, all forms of non-volatile memory, such as semiconductor memory devices, including EPROM, EEPROM, and flash memory devices; magnetic disks such as internal hard disks and removable disks; magneto-optical disks; and CD-ROMs. Any of the foregoing may be supplemented by, or incorporated in, specially-designed ASICs (application-specific integrated circuits) or FPGAs (Field-Programmable Gate Arrays). A computer can generally also receive (read) programs and data from, and write (store) programs and data to, a non-transitory computer-readable storage medium such as an internal disk (not shown) or a removable disk.

[028] The present disclosure provides a computer implemented method and system of predicting occurrence of one or more natural disasters for preventing data loss and infrastructure outage.

[029] The present disclosure envisages the system which can prevent data loss infrastructure outage caused by said one or more natural disasters by designing a location based natural disaster alert mechanism by predicting said one or more natural disasters by extracting natural disaster alert data from web.

[030] Referring to Figure 1, it is a flow chart illustrating method for data migration for preventing data loss and computational infrastructure outage based on prediction of one or more natural disasters.
[031] The process starts at step 102, data pertaining to natural disasters is received from a plurality of data sources. At step 104, the data received is processed to extract parameters related to the natural disasters. At step 106, the extracted parameters are analysed to predict the occurrence of the natural disasters. At step 108, based on the predicted occurrence of the natural disasters, prevention of data loss and infrastructure outage is actuated by selecting one option from a group comprising of data transfer, data backup, data migration and data replication.

[032] Referring to Figure 2, it is a block diagram of a system for predicting occurrence of one or more natural disasters for preventing data loss and infrastructure outage. The system comprises of a data reception module (202), a data processing module (204), a data analysis and prediction module (206) and a data loss prevention module (208). Referring to Figure 3, the data processing module (204) further comprises of a historical data repository (302), a real time data repository (304), a predicted data repository (306), a web analytics engine (308) and a predictive analytics engine (310). Referring to Figure 4, the web analytics engine (308) further comprises of a web crawling module (402), a web mining module (404) and a web analysis module (406).

[033] According to an embodiment of the invention, the method for predicting occurrence of one or more natural disasters for preventing data loss and infrastructure outage comprises of receiving data pertaining to said one or more natural disasters from the plurality of data sources using the data reception module (202), processing said received data to extract one or more parameters related to said one or more natural disasters using the data processing module (204), analysing said extracted one or more parameters to predict the occurrence of said one or more natural disasters using the data analysis and prediction module (206) and preventing data loss and infrastructure outage based on the predicted occurrence of said one or more natural disasters using the data loss prevention module (208).

[034] According to another embodiment of the invention, natural disasters can broadly be of three categories- geological disasters, hydrological disasters and meteorological disasters. Geological disasters can be exemplified by earthquakes; hydrological disasters can be exemplified by flood and tsunami; and meteorological disasters are exemplified by storm and tornado.

[035] According to another embodiment of the invention, the plurality of data sources comprises of the historical data repository (302), the real time data repository (304) and the predicted data repository (306) pertaining to said one or more natural disasters. The historical data repository contains weather data and data pertaining to natural disasters of the past twenty-five years from numerous governmental weather websites. The real time data repository (304) extracts real time climate condition data from numerous websites and the predicted data repository (306) contains forecasted weather dataset and predicted natural disaster alerts from numerous websites. The data repositories contain historical, real time and predicted natural disaster alert of numerous disasters. Some examples of such natural disasters are earthquakes, tornadoes, storms, floods and tsunamis. The data pertaining to natural disasters are collected multiple times in a day to keep the data repository updated.

[036] According to another embodiment of the invention, the real time data pertaining to natural disasters are extracted from the real time data repository (304) using the web analytics engine (308). The web analytics engine (308) is communicatively coupled with the real time data repository (304). The different elements pertaining to natural disasters are mined from numerous websites on a real time basis and the parameters of the natural disasters are extracted from the web elements by using the web analytics engine (308).

[037] According to another embodiment of the invention, the web analytics engine (308) performs web crawling, web mining and web analysis while extracting real time data pertaining to said one or more natural disasters from the real time data repository (304) by using a web crawling module (402), a web mining module (404) and a web analysis module (406) respectively.

[038] According to another embodiment of the invention, the predicted data pertaining to natural disasters are extracted from the predicted data repository (306) using the predictive analytics engine (310). The predictive analytics engine (310) is communicatively coupled with the predicted data repository (306). The different pertaining to natural disasters are mined from the numerous websites multiple times in a day and the parameters of the natural disasters are extracted from the web elements by using the predictive analytics engine (310).

[039] According to another embodiment of the invention, the extracted parameters are analysed to predict whether there will be any occurrence of any natural disaster by using data analysis and prediction module (206). In case there is a prediction of a natural disaster at a user specified location, then the data loss prevention module (208) actuates the prevention of data loss and infrastructure outage by providing the user the right to select at least one option from a group comprising of data migration, data backup, data replication and data transfer.

[040] According to another embodiment of the invention, prevention of data loss and infrastructure outage by the data loss prevention module (208) by performing data migration is achieved by migrating data from one or more source data center to one or more destination data center wherein said one or more source data center is predicted to be struck with said one or more natural disasters and said one or more destination data center is outside the purview of predicted said one or more natural disasters.

[041] According to an exemplary embodiment of the invention, real time data are gathered about earthquakes into the real time data repository. There are government agencies to monitor and report earthquakes, assess earthquake impacts and hazards, and research the causes and effects of earthquakes. These agencies display the earthquake related data and alerts in their respective websites. The data and details for any earthquake related event that occurs anywhere in the world gets updated on these websites in real time. This data is received and mined from such numerous websites by the data reception module (202). The parameters required for analysis of earthquakes are timestamp of the earthquake, magnitude and affected locations. As a result, the cited parameters are extracted from the earthquake related data by using the data processing module (204). It has been noticed that not all the earthquakes are catastrophic. In fact, earthquakes of magnitude of 4.0 and above on the Richter scale are the ones which tend to have hazardous ramifications; earthquakes of magnitude of 4.0 and above on the Richter scale tends to be dangerous with potential to cause economic and human loss. The data analysis and prediction module (206) analyses the extracted parameters to examine whether the parameters display any earthquake prediction for the user specified locations that would be of magnitude of 4.0 and above on the Richter scale. In case there is any prediction of any occurrence of such an event, the data loss prevention module (208) actuates the prevention of data loss and infrastructure outage by providing the user the right to select at least one option from a group comprising of data migration, data backup, data replication and data transfer from a source data center to a destination data center wherein the source data center is in a location where earthquake is being predicted to take place to a destination data center that is located outside the purview of the predicted earthquake.

[042] According to another exemplary embodiment of the invention, predicted data from the predicted data repository (306) is used to predict the occurrence of meteorological disasters of the categories of storm and tornado. The predicted data repository (306) gathers such data from the government websites. The predictive analytics engine (310) mines the data from the websites. These data includes information such as date on which the storms or tornadoes can affect a city, severity and category of storm and tornado based on the intensity and locations which might get affected. The data processing module (204) extracts the cited parameters for further analysis by the data analysis and prediction module (206). The categories of storms and tornadoes in increasing severity order include marginal, slight, enhanced, moderate and high. It has been noticed and observed over the years that any severity of enhanced category or above tends to be destructive in nature. As a result, the data analysis and prediction module (206) analyses the parameters to check whether any storm or tornado of enhanced category or above is being predicted to occur in a location as chosen by the user. In case there is any prediction of any occurrence of such an event, the data loss prevention module (208) actuates the prevention of data loss and infrastructure outage by providing the user the right to select at least one option from a group comprising of data migration, data backup, data replication and data transfer from a source data center to a destination data center wherein the source data center is in a location where occurrence of such tornado or storm is being predicted to take place to a destination data center that is located outside the purview of the predicted tornado or storm.

[043] According to yet another exemplary embodiment of the invention, historical data from the historical data repository (302) and predicted data from the predicted data repository (306) is used to predict the occurrence of floods. Historical data with daily record is collected for the respective cities for a duration of the last 25 years. The climatic conditions that might result in rain differ from one location to another. As an example, the atmospheric conditions that causes rain in coastal area will be different than the conditions that can cause rain in inland. Therefore, location based rain and flood prediction system is required and historical weather dataset for respective locations are collected for that purpose. Predicted data is also gathered in the predicted data repository (306) for the user specified locations. The data processing module (204) processes the received data to extract the parameters which includes temperature, humidity, wind speed, wind degree, dew point, visibility, gust speed, sea level pressure, precipitation.

[044] Flood occurs due to continuous rain and/or hurricanes. In order to design a system that raises alert for flood, there is need to predict the likelihood of rain and the amount of precipitation. Every location has a specific threshold value for water level or precipitation amount above which there will be flood in the area. This rise in water level can be caused due to frequent and continuous rain. To facilitate this, a rain and precipitation prediction system is designed using twenty-five year location specific historical weather dataset collected every day.

[045] The data analysis and prediction module (206) analyses all the parameters extracted from historical data about the user specified locations and the occurrence of past floods with the extracted parameters of the predicted data to examine whether the parameters predict the occurrence of flood. Based on this predicted values, if the values exceeds a specific threshold value of location based flood water level, then a flood alert is issued for the location.

[046] In an embodiment of the invention, in the first phase to predict the occurrence of floods, a rain and precipitation prediction system is designed using 25-year location/city specific historical weather dataset collected every day. The historical dataset is extracted from websites by using Perl programming. The dataset is structured and labeled as R if the precipitation amount for the day record is more than 0 or as NR otherwise. The labeled data is stored in Greenplum database to use it for Machine Learning classification. Data Analytics tool such as RapidMiner is used to design the Machine Learning classification workflow. Two separate prediction models are created, one model is used for predicting the likelihood of rain event and the other model is used to predict the precipitation amount. For first model, the dataset is randomly split in 65:35 proportions. The first part of 65% data is labelled as training_data and it is used as the input for the Naive Bayes operator in Machine Learning-Training phase and the remaining 35% data is labelled as validation_data and it is kept for use in the Machine Learning-Evaluation phase. Read_Database operator in RapidMiner is used to read the labeled data using SQL queries and table name. Useful data attributes, on which rain event depends, are selected and fed as input to Naïve Bayes Kernel operator. The attributes selected are mean temperature, mean humidity, mean wind speed, wind degree, mean dew point, mean visibility, precipitation amount and labels. For second model, only the dataset corresponding to rain event (i.e. data rows labeled as R only) is taken and is randomly split in 80:20 proportions. The first part of 80% data is labelled as training_data and it is used as the input for the Linear Regression operator in Machine Learning-Training phase and the remaining 20% data is labelled as validation_data and it is kept for use in the Machine Learning-Evaluation phase. Read_Database operator reads the data only related to the rain events (data labeled as R) and useful data attributes are selected. Linear Regression algorithm is applied over this labeled data. Naïve Bayes Kernel classifier is used to classify or predict the rain and no rain events and the Linear Regression is used to predict the amount of precipitation on the day of rain event.

[047] In an embodiment of the invention, in the second phase to predict the occurrence of floods, the validation_data is given as input to the two learned models. Though the data is labelled, the label will not be fed into the Naive Bayes and Linear Regression algorithms. The training_data and validation_data should have same attribute names. The label is used to check the correctness of predictions made by the learned model. The Machine Learning-Evaluation phase is implemented using Data Analytics tool such as RapidMiner. RapidMiner'sapply_model operator is used to invoke the learned model and validation_data. The workflow execution will append the prediction columns with the columns of the input dataset into a prediction table as specified by user. The above mentioned processes are followed by both Naïve Bayes Kernel classifier and Linear Regression algorithms and the results from both models are stored separately. The output from Naive Bayes is provided to performance_validation which evaluates prediction accuracy of the learned model in terms of percent accuracy, classification error, absolute error, relative error, root mean squared error, root relative error and correlation. The output from Linear Regression is provided to the input of performance_validation operator, which evaluates the prediction accuracy in terms of same metrics as above, plus prediction average attribute.

[048] In an embodiment of the invention, the final phase in the flood prediction system involves gathering future weather outlook dataset from weather channels using Python Spider. The crawled data is parsed and useful information and data fields are extracted from the XML or HTML file using XPath. Python program is used to filter and structure the raw data to create the future dataset. This dataset is used with the cited first learned model for rain event prediction. In the Rapid Miner Analytics process, same attributes are selected as used during the Machine Learning - Training phase, except the events column, and is fed into the model. The saved Naïve Bayes model is invoked for rain event prediction. If there is no rain and no existing flood alerts then appropriate message is stored in database. If there is likelihood of rain on any given day, the same dataset is passed to the second learned model which uses Linear Regression for prediction of precipitation amount. Based on this predicted values, if the values exceeds a specific threshold value of location based flood water level, then a flood alert is issued for the location.