Description:FIELD OF THE INVENTION
[0001] This invention generally relates to a field of natural disasters and, in particular relates to a system and method for predicting risk of occurrence of a natural disaster in a terrain.

BACKGROUND
[0002] The subject matter discussed in the background section should not be assumed to be prior art merely as a result of its mention in the background section. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches, which in and of themselves may also correspond to implementations of the claimed technology.
[0003] Predicting the risk of natural disasters is critical for ensuring public safety, efficient resource allocation, and effective disaster management. Conventionally, disaster risk assessments often rely on manual surveys and historical data analysis, which are not always provide real-time or terrain-specific insights. These manual methods involve significant effort, time, and expertise to evaluate various parameters, such as terrain characteristics, weather patterns, and historical occurrences. Additionally, manual assessments are prone to human error and inconsistencies, which impact the accuracy of the predictions. Moreover, the reliance on historical data alone does not account for rapidly changing environmental conditions, thereby limiting the effectiveness of such methods in predicting risks accurately.
[0004] Furthermore, existing systems for monitoring terrain conditions often rely on individual sensor readings or localized data without integrating multiple data sources. For instance, systems that utilize only images or limited sensor data fail to provide a comprehensive analysis of the terrain's risk factors. These limitations hinder the ability to assess complex terrains such as mountainous regions, wetlands, or coastal areas, where multiple dynamic factors like soil composition, moisture levels, and slope stability interact.
[0005] According to a patent application “CN111052772A” titled “Method and system for secure tracking and generating alerts” discloses computerized methods for monitoring, analysing, normalizing, applying, predicting, etc., various conditions. The method may include receiving data from a source over a channel, generating a report based on the data. The report may contain information associated with one or more events, the information being compiled in a standardized format in response to determining that the report corresponds to the first existing incident. The method may include supplementing an existing incident with the reported information, the existing incident being one of a plurality of existing incidents stored in a database and including information corresponding to one or more events at a specified location and at a specified time. The method may further include generating a location score at the specified location, and/or a security score for the individual, object, and/or property at the specified location.
[0006] According to a patent application “US20210233388A1” titled “predictive analytics for emergency detection and response management” discloses systems, methods, and media capable of generating emergency predictions. The systems, methods, and media generate spatiotemporal emergency communication predictions, carry out data augmentation, detect emergency anomalies, optimize emergency resource allocation, or any combination thereof.
[0007] However, the existing systems for natural disaster or risk prediction often suffer from inefficiencies due to limited data integration, lack of real-time analysis, and inadequate visualization tools. Further, these systems fail to incorporate diverse terrain types or provide user-friendly interfaces for risk communication. Thus, there remains a need for a system that integrates multiple data sources, normalizes inputs, and predicts the risk of natural disasters effectively.
OBJECTIVES OF THE INVENTION
[0008] The objective of invention is to provide a system and method for predicting risk of natural disaster that leverages artificial intelligence and machine learning for predicting risk of occurrence of the natural disaster.
[0009] The objective of invention is to provide the system and method for predicting risk of natural disaster based on visual images and characteristics of a terrain.
[0010] Furthermore, the objective of present invention is to provide the system and method for predicting risk of natural disaster in accessible format for disaster management.
[0011] Furthermore, the objective of present invention is to provide the system and method for predicting risk of natural disaster capable of generating alerts, aiding in timely decision-making and mitigation strategies.
[0012] Furthermore, the objective of present invention is to provide the system and method for predicting risk of natural disaster that is accurate and reliable.

SUMMARY
[0014] According to an aspect, the present embodiments disclose a system for predicting risk of a natural disaster. Further, the system comprises an image capturing module to capture plurality of images of a terrain, plurality of sensors installed in the terrain to determine one or more characteristics of the terrain, a user interface communicatively coupled with the image capturing module and the plurality of sensors, the user interface is configured to input the plurality of images and the one or more characteristics of the terrain and at least one processor communicatively coupled with the user interface. The at least one processor is configured to normalise the one or more characteristics of the terrain fed as input in the user interface and predict a risk percentage of the terrain based at least on the plurality of images and the one or more characteristics of the terrain normalised.
[0015] According to an aspect, the image capturing module corresponds to one or more cameras. Further, the terrain corresponds to a mountainous terrain, a flat terrain, a desert terrain, a coastal terrain, a wetland terrain or alike. Further, the user interface is configured to display the risk percentage of the terrain as at least one infographic via the at least one processor. Further, the at least one infographic includes graphs, pie chart or matrix representations. Further, the plurality of sensors includes moisture sensor, depth sensor or composition sensor. Further, the user interface comprises an alert module to generate a notification in an instance when the risk percentage of the terrain is more than a threshold value.
[0016] According to an aspect, the present embodiments a method for predicting risk of a natural disaster is disclosed. Further, the method comprises capturing, via an image capturing module, plurality of images of a terrain, determining, via plurality of sensors installed in the terrain, one or more characteristics of the terrain, inputting, via a user interface coupled to the image capturing module and the plurality of sensors, the plurality of images and the one or more characteristics of the terrain, normalising, via at least one processor communicatively coupled with the user interface, the one or more characteristics of the terrain fed as input in the user interface and predicting, via the least one processor, a risk percentage of the terrain based at least on the plurality of images and the one or more characteristics of the terrain normalised.

BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The accompanying drawings illustrate various embodiments of systems, methods, and embodiments of various other aspects of the invention. Any person with ordinary skills in the art will appreciate that the illustrated element boundaries (e.g., boxes, groups of boxes, or other shapes) in the figures represent one example of the boundaries. It may be that in some examples one element may be designed as multiple elements or that multiple elements may be designed as one element. In some examples, an element shown as an internal component of one element may be implemented as an external component in another, and vice versa. Furthermore, elements may not be drawn to scale. Non-limiting and non-exhaustive descriptions are described with reference to the following drawings. The components in the figures are not necessarily to scale, emphasis instead being placed upon illustrating principles.
[0018] FIG. 1 illustrates a block diagram of a system for predicting risk of a natural disaster, according to an embodiment of the present invention;
[0019] FIG 2 illustrates a flowchart of the system for predicting risk of a natural disaster, according to an embodiment of the present invention;
[0020] FIG. 3 illustrates a plurality of images of a terrain, according to an embodiment of the present invention;
[0021] FIG. 4 illustrates a table showing one or more characteristics of the terrain, according to an embodiment of the present invention;
[0022] FIG. 5 illustrates a detailed flowchart of the system, according to an embodiment of the present invention;
[0023] FIGS. 6A – 6B illustrate a pictorial representation of a user interface, according to an embodiment of the present invention; and
[0024] FIG. 7 illustrates a flowchart of a method for predicting risk of a natural disaster, according to an embodiment of the present invention.

DETAILED DESCRIPTION
[0026] Some embodiments of this invention, illustrating all its features, will now be discussed in detail. 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. 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.
[0027] 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. Embodiments of the present invention will be described more fully hereinafter with reference to the accompanying drawings in which like numerals represent like elements throughout the several figures, and in which example embodiments are shown. Embodiments of the claims may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. The examples set forth herein are non-limiting examples and are merely examples among other possible examples.
[0028] The present invention discloses about a system and method for predicting risk of a natural disaster in a terrain based on artificial intelligence and machine learning based analysis of visual and technical characteristics of the terrain.
[0029] FIG. 1 illustrates a block diagram of a system (100) for predicting risk of a natural disaster, according to an embodiment of the present invention. FIG 2 illustrates a flowchart (200) of the system (100) for predicting risk of a natural disaster, according to an embodiment of the present invention. FIG. 3 illustrates a plurality of images (300) of a terrain according to an embodiment of the present invention. FIG. 4 illustrates a table (400) showing one or more characteristics of the terrain, according to an embodiment of the present invention. FIG. 1 is explained in conjunction with FIGS. 2-4.
[0030] In some embodiments, the system (100) comprises an image capturing module (102), plurality of sensors (104), a user interface (106) and at least one processor (108). In some embodiments, the image capturing module (102) corresponds to one or more cameras. Further, the image capturing module (102) is installed at different locations in a terrain. The image capturing module (102) is positioned to capture diverse angles and perspectives of the terrain (300). The image capturing module (102) is configured to capture high-resolution ground-level based plurality of images (300) (shown in FIG. 3) that reflect real time conditions of the terrain accurately. In some embodiments, the terrain corresponds to a mountainous terrain, a flat terrain, a desert terrain, a coastal terrain, a wetland terrain or alike.
[0031] In some embodiments, the plurality of sensors (104) are installed in the terrain. Further, the plurality of sensors (104) are configured to determine one or more characteristics of the terrain. In some embodiments, the plurality of sensors (104) include moisture sensor, depth sensor or composition sensor. In some embodiments, the one or more characteristics of the terrain include composition of soil of the terrain, soil penetration, moisture percentage of soil or alike. The plurality of sensors (104) may be configured to measure critical parameters such as soil moisture content, depth variations, and soil composition, providing a detailed understanding of the terrain's physical and environmental conditions. Further, in some embodiments, the one or more characteristics of the terrain include parameters that influence the stability of the terrain.
[0032] In some embodiments, the user interface (106) may be communicatively coupled to the image capturing module (102) and the plurality of sensors (104). In some embodiments, the user interface (106) is configured to input the plurality of images (300) and the one or more characteristics of the terrain. In some embodiments, the user interface (106) is installed in a computing unit. In an example, the computing unit may be a mobile phone, tablet, laptop, portable desktop, desktop or alike. In some embodiments, the user interface (106) may include a home page. Further, the home page may include plurality of options. In some embodiments, the plurality of options may be in the form of a drop down menu, an upload section or a text input bar. In some embodiments, a user may input information about the terrain by accessing the plurality of options of the user interface (106). In some embodiments, the input information may include the plurality of images (300) of the terrain captured by the image capturing module (102) and the one or more characteristics of the terrain detected by the plurality of sensors (104).
[0033] In some embodiments, the system (100) further comprises at least one processor (108) communicatively coupled with the user interface (106). In some embodiments, the at least one processor (108) is configured to normalise the one or more characteristics of the terrain fed as input in the user interface (106). The normalisation of the one or more characteristics of the terrain involves standardizing data related to the one or more characteristics collected from the plurality of sensors (104)) to ensure consistency and compatibility.
[0034] In an example, soil composition, moisture content, and penetration levels may be measured in varying units or scales. The at least one processor (108) may employ appropriate scaling, transformation, or statistical techniques to align the one or more characteristics to a uniform scale or format. By eliminating inconsistencies and irregularities in the one or more characteristics, the normalization ensures that the normalised one or more characteristics are accurate and ready for further predictive analysis. In an example, FIG. 4 shows one or more characteristics as the table (400) for the terrain (e.g., mountainous terrain) shown in the plurality of images (300). The one or more characteristics shown in the table 400 herein include soil composition, penetration level and location (latitude, longitude) with respect to the plurality of images (300). The one or more characteristics in the form of the table (400) may be uploaded, mentioned in the text bar or selected from one or more drop down menus in the user interface (106).
[0035] In one embodiments, the at least one processor (108) may predict a risk percentage of the terrain based at least on the plurality of images (300) and the one or more characteristics of the terrain normalised. In some embodiments, the user interface (106) is configured to display the risk percentage of the terrain as at least one infographic via the at least one processor (108). In some embodiments, the at least one infographic includes graphs, pie chart or matrix representations. In some embodiments, the at least one processor (108) may employ artificial intelligence (AI) and machine learning (ML) algorithms, such as deep learning or statistical models using TensorFlow and Keras protocols, to integrate the normalized one or more characteristics of the terrain with the plurality of images (300) of the terrain, extracting patterns and correlations indicative of potential risks.
[0036] In some embodiments, the user interface (106) is configured to display the predicted risk percentage of the terrain through infographics generated by the at least one processor (108). The infographics may include graphical representations such as bar graphs, pie charts, or matrix-based heat maps, providing the user with an intuitive and clear understanding of the risk percentage. The use of infographics aids in interpreting the data effectively, allowing stakeholders, such as disaster management authorities or local governments, to make informed decisions. The user interface (106) displays infographics in a user-friendly format, enabling quick assessment and action, particularly in high-risk scenarios such as landslides on mountainous terrain.
[0037] In one embodiments, the user interface (106) comprises an alert module to generate a notification in an instance when the risk percentage of the terrain is more than a threshold value. In an example, the user interface (106) includes the alert module configured to generate notifications when the risk percentage of the terrain, as predicted by the at least one processor (108), exceeds a predefined threshold value. The at least one processor (108) is configured to compare the predicted risk percentage against the threshold value. The threshold value may be adjusted based on the specific requirements of the terrain being monitored, such as the geographical characteristics, historical risk data, or local environmental conditions.
[0038] In an example, when the predicted risk percentage exceeds the threshold, value, the alert module triggers a notification to inform the user. The notification may be delivered in various formats, such as visual alerts on the user interface (106), audio alarms, or digital messages sent to the user through connected communication channels, including email, SMS, or mobile applications. In some embodiments, the user may be relevant stakeholders such as officials from disaster management, local authorities or residents. The alert module ensures that relevant stakeholders, such as disaster management teams, local authorities, or residents, are promptly informed about the elevated risk, enabling the user to implement preventive measures or evacuate the terrain, as necessary.
[0039] FIG. 5 illustrates a detailed flowchart (500) of the system (100), according to an embodiment of the present invention. FIGS. 6A-6B illustrate a pictorial representation (600, 602) of a user interface (106), according to an embodiment of the present invention. FIG. 5 is explained in conjunction with FIGS. 6A-6B.
[0040] In some embodiments, the system (100) comprises the user interface (106). The user interface (106) enables the user to input the plurality of images (300) and the one or more characteristics of the terrain as shown in the detailed flowchart (500) (FIG. 5). In an example, the user interface (106) may include an upload section and plurality of drop-down menus. For example, as shown in pictorial representation (600) of FIG. 6A, the user may upload the plurality of images (300) using the upload section. Further, the user may input one or more characteristics by using the drop-down menus such as for soil composition and penetration level as shown in FIG. 6A. Further, the user may click on the ‘PREDICT’ option to initiate integration of the plurality of images (300) and the one or more characteristics.
[0041] In some embodiments, the image capturing module (102) may be installed at various locations of the terrain. In some embodiments, the plurality of sensors (104) may be installed in the terrain. In some embodiments, the plurality of sensors (104) may include moisture sensor, depth sensor or composition sensor to determine one or more characteristics of the terrain. The one or more characteristics may include composition of soil of the terrain, soil penetration, moisture percentage of soil or alike. In an example, the plurality of sensors (104) may be installed in contact with soil of the terrain.
[0042] In some embodiments, the at least one processor (108) may normalise the one or more characteristics of the terrain fed as input in the user interface (106). The at least one processor (108) may employ appropriate scaling, transformation, or statistical techniques to align the one or more characteristics to a uniform scale or format. In one embodiments, the at least one processor (108) may predict a risk percentage of the terrain based at least on the plurality of images (300) and the one or more characteristics of the terrain normalised.
[0043] In some embodiments, the user interface (106) is configured to display the risk percentage of the terrain as at least one infographic such as graphs, pie chart or matrix representations. In some embodiments, the at least one processor (108) may employ artificial intelligence (AI) and machine learning (ML) algorithms, such as deep learning or statistical models using TensorFlow and Keras protocols, to integrate the normalized one or more characteristics of the terrain with the plurality of images (300) of the terrain, extracting patterns and correlations indicative of potential risks. Further, the at least one processor (108) displays the risk percentage of the terrain on the user interface (106), as shown in the pictorial representation (602) of FIG. 6B.
[0044] In an example, the at least one processor (108) may display the risk percentage of the terrain as at least one infographic. In an example, as shown in FIG. 6B, the infographic may be a confusion matrix that shows the outcome of the system (100). The confusion matrix contains four quadrants representing the number of true positives, false positives, true negatives, and false negatives. Each quadrant is color-coded, where darker shades indicate higher frequencies of prediction, offering a visual insight into performance of the system (100). In FIG. 6B, the system (100) via the at least one processor (108), accurately predicted 156 instances of Class 0 (safe terrain) and 160 instances of Class 1 (risky terrain). The false positives (Class 0 incorrectly predicted as Class 1) were 8 instances, while false negatives (Class 1 incorrectly predicted as Class 0) were 4 instances. Additional metrics, such as class-wise accuracy, are presented above the confusion matrix. For example, Class 0 has an accuracy of 95%, and Class 1 has an accuracy of 98%, reflecting that outcome of the system (100) is accurate and reliable.
[0045] FIG. 7 illustrates a flowchart of a method (700) for predicting risk of a natural disaster, according to an embodiment of the present invention.
[0046] At operation (702), the image capturing module (102) may capture the plurality of images (300) of the terrain. Further, the image capturing module (102) is installed at different locations in a terrain. The image capturing module (102) is positioned to capture diverse angles and perspectives of the terrain. The image capturing module (102) is configured to capture high-resolution ground-level images (300) that reflect real time conditions of the terrain accurately. In some embodiments, the terrain corresponds to a mountainous terrain, a flat terrain, a desert terrain, a coastal terrain, a wetland terrain or alike. In an example, the terrain may be a mountain terrain with risk of landslide.
[0047] At operation (704), the plurality of sensors (104) installed on the terrain may determine the one or more characteristics of the terrain. In some embodiments, the plurality of sensors (104) include moisture sensor, depth sensor or composition sensor. In some embodiments, the one or more characteristics of the terrain include composition of soil of the terrain, soil penetration, moisture percentage of soil or alike. The plurality of sensors (104) may be configured to measure critical parameters such as soil moisture content, depth variations, and soil composition, providing a detailed understanding of the soil around the mountain terrain including physical and environmental conditions. In an example, the one or more characteristics include parameters that influence the soil binding or other factors responsible for landslides in mountain terrains.
[0048] At operation (706), a user may input the plurality of images (300) of the terrain and the one or more characteristics of the terrain into the user interface (106) communicatively coupled to the image capturing module (102). In an example, the user may access the user interface (106) and upload the plurality of images (300) through an upload section (as shown in FIG. 6A). Further, the user may select the one or more drop down menus to input the one or more characteristics regarding the soil parameters of the mountain terrain.
[0049] Further, at operation (708), the at least one processor (108) may normalise the one or more characteristics of the terrain fed as input in the user interface (106). In some embodiments, the at least one processor (108) employ appropriate scaling, transformation, or statistical techniques to align the one or more characteristics to a uniform scale or format. By eliminating inconsistencies and irregularities in the one or more characteristics, the normalization ensures that the normalised one or more characteristics are accurate and ready for further predictive analysis.
[0050] Furthermore, at operation (710), the at least one processor (108) may predict a risk percentage of the terrain based at least on the plurality of images (300) and the one or more characteristics of the terrain normalised. In some embodiments, the at least one processor (108) may employ artificial intelligence (AI) and machine learning (ML) algorithms, such as deep learning or statistical models using TensorFlow and Keras protocols, to integrate the normalized one or more characteristics of the terrain with the plurality of images (300) of the terrain, extracting patterns and correlations indicative of potential risks. In an example, the at least one processor (108) via the user interface (106) may display the risk percentage corresponding to occurrence of landslide on the mountainous terrain.
[0051] It has thus been seen that the system for predicting risk of a natural disaster, as described. The system for predicting risk of a natural disaster in any case could undergo numerous modifications and variants, all of which are covered by the same innovative concept; moreover, all of the details can be replaced by technically equivalent elements. In practice, the components used, as well as the numbers, shapes, and sizes of the components can be whatever according to the technical requirements. The scope of protection of the invention is therefore defined by the attached claims.
, Claims:We Claim:
1. A system (100) for predicting risk of a natural disaster, the system comprises:
an image capturing module (102) configured to capture plurality of images (300) of a terrain;
plurality of sensors (104) installed in the terrain, wherein the plurality of sensors (104) is configured to determine one or more characteristics of the terrain;
a user interface (106) communicatively coupled with the image capturing module (102) and the plurality of sensors (104), wherein the user interface (106) is configured to input the plurality of images (300) and the one or more characteristics of the terrain; and
at least one processor (108) communicatively coupled with the user interface (106), wherein the at least one processor (108) is configured to:
normalise the one or more characteristics of the terrain fed as input in the user interface (106); and
predict a risk percentage of the terrain based at least on the plurality of images (300) and the one or more characteristics of the terrain normalised.

2. The system (100) as claimed in claim 1, wherein the image capturing module (102) corresponds to one or more cameras.

3. The system (100) as claimed in claim 1, wherein the terrain corresponds to a mountainous terrain, a flat terrain, a desert terrain, a coastal terrain, a wetland terrain or alike.

4. The system (100) as claimed in claim 1, wherein the user interface (106) is configured to display the risk percentage of the terrain as at least one infographic via the at least one processor (108).

5. The system (100) as claimed in claim 4, wherein the at least one infographic includes graphs, pie chart or matrix representations.

6. The system (100) as claimed in claim 1, wherein the plurality of sensors (104) includes moisture sensor, depth sensor or composition sensor.

7. The system (100) as claimed in claim 1, wherein the user interface (106) comprises an alert module to generate a notification in an instance when the risk percentage of the terrain is more than a threshold value.

8. A method (700) comprising:
capturing, via an image capturing module (102), plurality of images (300) of a terrain;
determining, via plurality of sensors (104) installed in the terrain, one or more characteristics of the terrain;
inputting, via a user interface (106) coupled to the image capturing module (102) and the plurality of sensors (104), the plurality of images (300) and the one or more characteristics of the terrain;
normalising, via at least one processor (108) communicatively coupled with the user interface (106), the one or more characteristics of the terrain fed as input in the user interface (106); and
predicting, via the least one processor (108), a risk percentage of the terrain based at least on the plurality of images (300) and the one or more characteristics of the terrain normalised.