A SYSTEM AND METHOD FOR MONITORING LANDSLIDE USING LORAWAN COMMUNICATION

Abstract

A system 100 to detect and monitor landslide to alert population can include a plurality of sensors 200 configured within a land area of interest; and a server 108 in communication with the plurality of sensors 200, a GPS module 104, and a network gateway 106. The at least one processor performs operations to collect real-time data using the plurality of sensors 200; analyze received data using machine learning algorithms specifically neural network trained on historical landslide data; identify patterns indicating imminent landslide within the land area of interest; classify conditions of the imminent landslide into standard categories; transmit emergency warning when the patterns classified as critical along with GPS coordinates of the imminent landslide site and sensor data to the server 106 and a central office 110; and transmit, by the central office 110, an initial SOS message to all mobile devices held by the population and direct them to the nearest safe location.

Specification

Description:TECHNICAL FIELD
[0001] The present disclosure relates to the field of landslide monitoring systems. In particular, the disclosure is about a system and method for detecting and monitoring landslides to alert population residing nearby to move to a safe location using long range wide area network (LoRaWAN) technology.

BACKGROUND
[0002] Background description includes information that may be useful in understanding the present disclosure. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed disclosure, or that any publication specifically or implicitly referenced is prior art.
[0003] Landslide is a common phenomenon in hilly regions. It is a natural disaster caused by the natural factors or results of various land activities purposely done by human on the name of development. The landslide, if occurs in populated area create large scale devastation involving deaths and loss of property. Countries with large percentage of hilly area, faces most landslides during rainy seasons and treating rain as main factor responsible for landslides. The slope is also considered a factor where more the steepness, larger the landslide occurs.
[0004] Though avoiding landslides is difficult, but predicting landslide and give early warning to the population is possible using technologies. Most of the methods for early identification and providing early warnings have reached near to accuracy. Methods, using SAR images to calculate deformation rates, study of weather phenomenon, using IoT devices provides improved accuracy.
[0005] Efforts have been made to solve the limitations and problems analysing real-time data and issue of early warning. For example, Patent Document CN109613513B discloses an optical remote sensing potential landslide automatic identification method considering InSAR deformation factor comprises steps for acquiring deformation rate image and optical remote sensing image of a target area for pre-processing; calculating topographic information data; a plurality of objects are obtained through segmentation according to the deformation rate graph, and ground feature classification samples are selected to obtain classification characteristics elements and thresholds values of various ground feature classification samples; classifying and eliminating to obtain a target area potential landslide area; calculating to obtain a potential landslide objects, combining the potential landslide object with the obtained potential landslide area, and finally obtaining a complete potential landslide area of the target area.
[0006] Another Patent Document KR102242977B1 discloses an early warning method and system for landslide with weather forecasting information predicting rainfall information by analysing prior weather information of a target area, and analysing surface flow of a target area. Ground penetration analysis and infinite slope stability analysis considering suction stress are performed to evaluate the possibility of landslides, and based on the possibility of landslides determine whether to issue early warning of landslides in consideration of the safety rate standards with uncertainty about the spatial distribution of soil properties was resolved by dividing the target area into a plurality of sub watersheds, and calculating the slope safety factor by performing Monte Carlo simulation on the soil properties for each mesh included with the sub watershed.
[0007] While the reference documents provides some characteristics for reliable prediction of landslide based on optical remote sensing potential landslide automatic identification method considering InSAR deformation factor, and analysing data for advanced weather information to issue early warning respectively, there is a possibility and scope to provide a system and method which is not based on above mentioned methods and can overcome the limitations of existing technologies by incorporating machine learning and neural network.
[0008] There is, therefore a need to have a simple, accurate, and cost-effective system and method for monitoring landslides and generate early warnings to population about the landslide using real-time data obtained by the network of sensors and using long range wide area network (LoRaWAN) technology to alert population in local area.


OBJECTS OF THE PRESENT DISCLOSURE
[0009] A general object of the present disclosure is to provide a system and method to issue early warning of landslides to population living in hilly areas using real-time data obtained by sensors even in adverse weather conditions.
[0010] An object of the present disclosure is to provide a simple, accurate, and cost-effective system and method using long rangeWAN communication technology to communicate early warning message.
[0011] An object of the present disclosure is to provide the system to intimate safe location for the local population in case of landslide using long range communication within free ISM band.
[0012] An object of the present disclosure is to provide uses of machine learning and neural network to identify probable landslide to warn local population.
[0013] Yet another object of the present disclosure is to provide the system that collects and analyse real-time data from various sensors for processing and environmental monitoring by machine learning algorithms.

SUMMARY
[0014] Aspects of the present disclosure relates to the field of landslide monitoring systems. In particular, the disclosure is about a system and method for detecting and monitoring landslides to alert population residing nearby to move to a safe location using long range wide area network (LoRaWAN) technology. The proposed system utilizes LoRaWAN for communication, integrated GPS capabilities, and machine learning algorithms to address high operational costs, poor coverage in remote areas, and data accumulation for detecting landslide to warn the population for a safe location.
[0015] According to aspect of the disclosure, the disclosure is a system to detect landslide and alert population can include a plurality of sensors configured within a land area of interest; and a server in communication with the plurality of sensors, a GPS module, and a plurality of long range communication nodes operating under wide area network gateway. The server including at least one centralized database and one or more processors communicatively coupled with memory storing instructions, when executed by one or more processors, causes at least one processor to perform operations to collect real-time data using the plurality of sensors configured with the land area of interest; analyze received data from the plurality of sensors using machine learning algorithms specifically neural network trained on historical landslide data; identify patterns from the received data indicating imminent landslide within the land area of interest; classify conditions of the imminent landslide into standard categories; transmit emergency warning when the patterns classified as critical along with GPS coordinates of the imminent landslide site and sensor data to the server and a central office using long range wide area network; and transmit, by the central office, a two-stage emergency message sending an initial SOS message to all mobile phones held by the population in the area to direct population to the nearest safe location.
[0016] In an aspect, the plurality of sensors includes soil moisture sensors, piezometers, gyroscopes, humidity sensors, and temperature sensors.
[0017] In an aspect, the plurality of sensors sense real-time data of soil moisture, pore water pressure, angle of tilt, rotation, and change in velocity of slope, humidity, and temperature of the atmosphere respectively, to detect changes in land parameters responsible for landslide.
[0018] In an aspect, the system combining piezometer data on pore water pressure with digital elevation models to monitor slope stability of the hilly land.
[0019] In an aspect, the system integrates the TTGO T-Beam ESP32 LoRaWAN GPS Module as a key component for real-time data processing and environmental monitoring.
[0020] In an aspect, the received data is continuously analyzed by machine learning algorithms embedded within the ESP32 microcontroller, and a neural network trained on historical landslide data.
[0021] In an aspect, the system processes data in real-time using TTGO T-Beam ESP32 LoRaWAN GPS Module, providing immediate alerts and speeding up response times to address delays in data processing.
[0022] In an aspect, the system, when identifies data patterns as 'Critical', triggers an emergency response, transmitting GPS coordinates and sensor data to the server via LoRaWAN gateway and a central office.
[0023] In an aspect, the central office generates a two-stage emergency messaging sending an initial SOS message to the nearest cell tower using a secure SMS API for broadcasting on all mobile devices held by the population in the local area about potential landslide event, and wherein a URL link utilizing mapping APIs is also generated directing users about the nearest safe location.
[0024] Another aspect of the disclosure is a method for detecting landslide and alerting population including steps for collecting real-time data using the plurality of sensors configured with the land area of interest; analyzing received data from the plurality of sensors using machine learning algorithms specifically neural network trained on historical landslide data; identifying patterns from the received data indicating imminent landslide within the land area of interest; classifying conditions of the imminent landslide into standard categories; transmitting emergency warning when the patterns classified as critical along with GPS coordinates of the imminent landslide site and sensor data to the server and a central office using long range wide area network; and transmitting, by the central office, a two-stage emergency message sending an initial SOS message to all mobile devices held by the population in the area and directing population to the nearest safe location.
[0025] Various objects, features, aspects, and advantages of the inventive subject matter will become more apparent from the following detailed description of preferred embodiments, along with the accompanying drawing figures in which like numerals represent like components.

BRIEF DESCRIPTION OF THE DRAWINGS
[0026] The accompanying drawings are included to provide a further understanding of the present disclosure, and are incorporated in and constitute a part of this specification. The drawings illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0027] FIG. 1 illustrates an exemplary block diagram for the system to monitor landslides using a sensor network and LoRaWAN communication, in accordance with an embodiment of the present disclosure.
[0028] FIG. 2 illustrates an exemplary information flow diagram for data collection and execution for landslide monitoring using LoRaWAN communication, in accordance with an embodiment of the present disclosure.
[0029] FIG. 3 illustrates an exemplary method diagram, in accordance with an embodiment of the present disclosure.

DETAILED DESCRIPTION
[0030] The following is a detailed description of embodiments of the disclosure depicted in the accompanying drawings. The embodiments are in such details as to clearly communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosures as defined by the appended claims.
[0031] Embodiments explained herein relate to the field of communication system. In particular, the disclosure is about a system and method for detecting and monitoring landslides to alert population residing nearby to move to a safe location using long range wide area network (LoRaWAN) technology.
[0032] In an embodiment, the disclosed system is to detect landslide and alert population can include a plurality of sensors configured within a land area of interest; and a server in communication with the plurality of sensors, a GPS module, and a network gateway. The at least one processor performs operations to collect real-time data using the plurality of sensors; analyze received data using machine learning algorithms specifically neural network trained on historical landslide data; identify patterns indicating imminent landslide within the land area of interest; classify conditions of the imminent landslide into standard categories; transmit emergency warning when the patterns classified as critical along with GPS coordinates of the imminent landslide site and sensor data to the server and a central office; and transmit, by the central office, an initial SOS message to all mobile devices held by the population and direct them to the nearest safe location.
[0033] In an embodiment, the plurality of sensors includes soil moisture sensors, piezometers, gyroscopes, humidity sensors, and temperature sensors to sense real-time data of soil moisture, pore water pressure, angle of tilt, rotation, and change in velocity of slope, humidity, and temperature of the atmosphere respectively.
[0034] In an embodiment, the system integrates the TTGO T-Beam ESP32 LoRaWAN GPS Module as a key component for real-time data processing and environmental monitoring. The received data is continuously analyzed by machine learning algorithms embedded within the ESP32 microcontroller, and a neural network trained on historical landslide data and processes data in real-time using TTGO T-Beam ESP32 LoRaWAN GPS Module, providing immediate alerts and speeding up response times to address delays in data processing.
[0035] In an embodiment, the system, when identifies data patterns as 'Critical', triggers an emergency response, transmitting GPS coordinates and sensor data to the server via LoRaWAN gateway and a central office. The central office generates a two-stage emergency messaging sending an initial SOS message to the nearest cell tower using a secure SMS API for broadcasting on all mobile devices held by the population in the local area about potential landslide event, and wherein a URL link utilizing mapping APIs is also generated directing users about the nearest safe location.
[0036] Referring to the FIG. 1 where an exemplary block diagram for system 100 to monitor landslides using a sensor network and LoRaWAN communication is shown.
[0037] In an embodiment, the detection of landslide and monitoring system 100 functions to alert central authorities and population about potential landslides in real-time. The system 100 leverages a combination of various sensors 200, machine learning algorithms, and long-range wireless communication to provide accurate and timely warnings.
[0038] In an embodiment, the system 100 to detect landslide and alert population can include a plurality of sensors 200 configured within a land area of interest; and a server 108 in communication with the plurality of sensors 200, a GPS module 104, a plurality of long range communication nodes operating under wide area network gateway 106. The server 108 including at least one centralized database and one or more processors communicatively coupled with memory storing instructions, when executed by one or more processors, causes at least one processor to perform operations.
[0039] In an embodiment, the plurality of sensors 200 includes soil moisture sensors 202, piezometers 204, gyroscopes 206, humidity sensors 208, and temperature sensors 210.
[0040] In an embodiment, the plurality of sensors 200 sense real-time data responsible for landslide using different sensors. The piezometer 204 measures the pore water pressure within the soil, which is another vital factor in assessing the possibility of a landslide. The gyroscope 206used with the system 100 is type- MPU 6050. The gyroscope is an Inertial Measurement Unit (IMU) that includes an accelerometer and gyro meter to read the rate of change of the velocity of the slope of the hilly area of interest. Also, the gyroscope measures the angle of tilt or inclination of the slope of the hilly land.
[0041] In an embodiment, the humidity sensor 208 monitors the humidity levels of the surrounding atmosphere. This can influence soil moisture a critical indicator of soil stability. The temperature sensor measures the ambient temperature, which can impact soil conditions and sensor readings.
[0042] In an embodiment, the system 100 integrates the TTGO T-Beam ESP32 LoRaWAN GPS Module 104 as central processing unit, a key component for real-time data processing and environmental monitoring. The module 104 collects data from the plurality of sensors 200, running machine learning algorithms, managing communication with the LoRaWAN gateway 106, and providing GPS location tracking.
[0043] In an embodiment, the long range wide area network (LoRaWAN) technology for transmitting data from sensors over long distances. LoRaWAN provides a significant advantage in terms of communication range and power efficiency, making it ideal for remote and difficult to access landslide-prone areas. This offers long-range communication capabilities of up to 15 km line of sight.
[0044] In an embodiment, the LoRaWAN includes sender module, LoRaWAN gateway 106, and SMS API. The sender module transmits the collected data to the LoRaWAN gateway. The LoRaWAN Gateway is Dragino LPS8v2, which receives and forwards data to the main server 108. The SMS API integrates with the system 100 to send SMS alerts to local population and central office 110 authorities about the detection of land slide.
[0045] In an embodiment, the power supply 102 to the TTGO T-Beam ESP32 LoRaWAN GPS Module 104 is given through a rechargeable battery. The battery is a rechargeable lithium battery serves as the primary power source, ensuring continuous operation even during power outages.
[0046] In an embodiment, to start with the detection of the landslide, the data from the plurality of sensors 200 is collected and processed in real-time by the TTGO T-Beam ESP32 LoRaWAN GPS Module 104. The received data is processed and analysed with machine learning algorithms on the TTGO T-Beam ESP32 LoRaWAN GPS Module 104 for the critical parameters.
[0047] In an embodiment, the system 100, when identifies data patterns as 'Critical', triggers an emergency response, transmitting GPS coordinates and sensor data to the server 108 via LoRaWAN gateway 106 and a central office 110 for further analysis and records.
[0048] In an embodiment, the central office 110 generates a two-stage emergency messaging sending an initial SOS message to the nearest cell tower 112 using a secure SMS API for broadcasting on all mobile devices held by the population 114 in the local area about potential landslide event, and wherein a URL link utilizing mapping APIs is also generated directing users about the nearest safe location.
[0049] FIG. 2 illustrates an exemplary information flow diagram for data collection and execution for landslide monitoring using LORAWAN communication.
[0050] In an embodiment, the power supply 112 to the TTGO T-Beam ESP32 LoRaWAN GPS Module 104 is ensured before going for the landslide detection operation. The TTGO T-Beam ESP32 LoRaWAN GPS Module 104 receives plurality of data from the plurality of sensors 200. The sensors 200 include soil moisture sensors 202, piezometers 204, gyroscopes 206, humidity sensors 208, and temperature sensors 210. The plurality of sensors 200 sense real-time data of soil moisture, pore water pressure, angle of tilt, rotation, and change in velocity of slope, humidity, and temperature of the atmosphere respectively, to detect changes in land parameters responsible for landslide.
[0051] In an embodiment, the TTGO T-Beam ESP32 LoRaWAN GPS Module 104 used for real-time data processing. The cutting-edge system 100, which combines sensors 200 and machine learning algorithms and a neural network trained on historical landslide data to predict landslides by analysing data on soil wetness, temperature, vibrations, and ground movement, using algorithms like Support Vector Machines for accurate predictions. When the at least three parameters received from the sensors 200 are exceeding thresholds values as analyzed by the block 212, a critical signal is generated by the module 104 to server 108 using the LoRaWAN gateway 106.
[0052] In an embodiment, the server sends SOS alerts, including map URLs, to local population and central office 110 via SMS API using cellular towers covering danger zones 112.
[0053] In an embodiment, in case of an SOS situation, the SOS message is sent via an SMS API from the server 108 to the cell tower covering the danger zones 214, which then sends SOS messages to the mobile devices connected to the cell tower and held by the local population for safe locations 218.
[0054] In an embodiment, when the local population receives the SMS with a link, they follow the link to a map URL showing the landslide location and directions to safer locations, facilitating prompt evacuation measures. The GPS Module 104 also provides GPS location tracking, enabling precise positioning of the landslide event and evacuation routes.
[0055] FIG. 3 illustrates an exemplary method diagram 300 for detecting landslide and alerting population to move to a safe location. The method 300 for detecting landslide and alerting population including step 302 for collecting real-time data using the plurality of sensors 200 configured with the land area of interest.
[0056] In an embodiment, according to step 304, analysing received data from the plurality of sensors 200 using machine learning algorithms specifically neural network trained on historical landslide data, for identifying patterns 212 from the received data indicating imminent landslide within the land area of interest, as per step 306.
[0057] In an embodiment, step 308 defining and classifying conditions of the imminent landslide into standard categories. As per step 310, transmitting emergency warning 218 when the patterns classified as critical along with GPS coordinates of the imminent landslide site and sensor data to the server 106 and a central office 110 using long range wide area network.
[0058] In an embodiment, as per step 312 transmitting, by the central office 110, a two-stage emergency message sending an initial SOS message to all mobile devices held by the population 218 in the area and directing population to the nearest safe location.
[0059] Thus, the proposed system 100 monitoring real-time data received from the sensors 200, processing and analysing using machine learning, results in more accurate landslide predictions. The timely alerts featuring long-range communication, and sustainable operation even in the most remote and large coverage areas in challenging environments. The disclosure is made simple and cost effective as power consumption is very low as well as the system 100 works efficiently even in adverse weather conditions.
[0060] It will be understood that the various data and figures described herein are merely exemplary and a person skilled in the art may appreciate that distinct comparison and modifications to the described embodiments using alternate technique and material embodiments will fall well within the scope of the invention.
[0061] While the foregoing describes various embodiments of the invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof. The scope of the invention is determined by the claims that follow. The invention is not limited to the described embodiments, versions or examples, which are included to enable a person having ordinary skill in the art to make and use the invention when combined with information and knowledge available to the person having ordinary skill in the art.

ADVANTAGES OF THE PRESENT INVENTION
[0062] The present disclosure provides a system and method to issue early warning of landslides to population living in hilly areas using real-time data obtained by sensors even in adverse weather conditions.
[0063] The present disclosure provides a simple, accurate, and cost-effective system and method using long range wide area network (LoRaWAN) communication technology to communicate early warning message.
[0064] The present disclosure provides the system to intimate safe location for the local population in case of landslide using long range communication within free ISM band.
[0065] The present disclosure provides uses of machine learning and neural network to identify probable landslide to warn local population.
[0066] The present disclosure provides the system that collects and analyse real-time data from various sensors for processing and environmental monitoring by machine learning algorithms.
, Claims:1. A system (100) to detect landslide and alert population, the system (100) comprising:
a plurality of sensors (200) configured within a land area of interest; and
a server (108) in communication with the plurality of sensors (200), a GPS module (104), a plurality of long range communication nodes operating under wide area network gateway (106), wherein the server (108) comprising at least one centralized database and one or more processors communicatively coupled with memory storing instructions, when executed by one or more processors, causes at least one processor to perform operations to:
collect real-time data using the plurality of sensors (200) configured with the land area of interest;
analyze received data from the plurality of sensors (200) using machine learning algorithms specifically neural network trained on historical landslide data;
identify patterns (212) from the received data indicating imminent landslide within the land area of interest;
classify conditions of the imminent landslide into standard categories;
transmit emergency warning (218) when the patterns classified as critical along with GPS coordinates of the imminent landslide site and sensor data to the server (106) and a central office (110) using long range wide area network; and
transmit, by the central office (110), a two-stage emergency message sending an initial SOS message to all mobile devices held by the population (218) in the area to direct population to the nearest safe location.
2. The system as claimed in claim 1, wherein the plurality of sensors (200) comprises soil moisture sensors (202), piezometers (204), gyroscopes (206), humidity sensors (208), and temperature sensors (210).
3. The system as claimed in claim 2, wherein the plurality of sensors (200) sense real-time data of soil moisture, pore water pressure, angle of tilt, rotation, and change in velocity of slope, humidity, and temperature of the atmosphere respectively, to detect changes in land parameters responsible for landslide.
4. The system as claimed in claim 3, wherein the system (100) combining piezometer (204) data on pore water pressure with digital elevation models to monitor slope stability of the hilly land.
5. The system as claimed in claim 1, wherein the system (100) integrates the TTGO T-Beam ESP32 LoRaWAN GPS Module (104) as a key component for real-time data processing and environmental monitoring.
6. The system as claimed in claim 5, wherein the received data is continuously analyzed by machine learning algorithms embedded within the ESP32 microcontroller, and a neural network trained on historical landslide data.
7. The system as claimed in claim 1, wherein the system (100) processes data in real-time using TTGO T-Beam ESP32 LoRaWAN GPS Module (104), providing immediate alerts and speeding up response times to address delays in data processing.
8. The system as claimed in claim 1, wherein the system (100), when identifies data patterns as 'Critical', triggers an emergency response, transmitting GPS coordinates and sensor data to the server (108) via LoRaWAN gateway (106) and a central office (110).
9. The system as claimed in claim 8, wherein the central office (110) generates a two-stage emergency messaging sending an initial SOS message to the nearest cell tower (112) using a secure SMS API for broadcasting on all mobile devices held by the population (114) in the local area about potential landslide event, and wherein a URL link utilizing mapping APIs is also generated directing users about the nearest safe location.
10. A method (300) for detecting landslide and alerting population, the method (300) comprising steps for:
collecting real-time data using the plurality of sensors (200) configured with the land area of interest;
analyzing received data from the plurality of sensors (200) using machine learning algorithms specifically neural network trained on historical landslide data;
identifying patterns (212) from the received data indicating imminent landslide within the land area of interest;
classifying conditions of the imminent landslide into standard categories;
transmitting emergency warning (218) when the patterns classified as critical along with GPS coordinates of the imminent landslide site and sensor data to the server (106) and a central office (110) using long range wide area network; and
transmitting, by the central office (110), a two-stage emergency message sending an initial SOS message to all mobile devices held by the population (218) in the area and directing population to the nearest safe location.

Documents