ELITE CODERS - Space Apps Challenge

ELITE CODERS| Automated Detection of Hazards

Automated Detection of Hazards

Countless phenomena such as floods, fires, and algae blooms routinely impact ecosystems, economies, and human safety. Your challenge is to use satellite data to create a machine learning model that detects a specific phenomenon and build an interface that not only displays the detected phenomenon, but also layers it alongside ancillary data to help researchers and decision-makers better understand its impacts and scope.

Heavy Rainfall and Flood Monitoring using DataAnalysis , IOT

Summary

This project focuses on predicting the flood using the rainfall dataset and providing alert messages to the communities who live near the dams/lakes/rivers. The data fetched from the water level sensor is constantly stored in a cloud server. This measurement of water level is displayed in a dashboard remotely so the people can easily monitor the water level wherever they live. The alert messages and relevant data regarding the level of water are transmitted to the cloud server and then it will be received by the consumers who are being owned through the user terminal. We converted our Analysis into a real-time solution for monitoring heavy floods by predicting in initial stage itself.

How We Addressed This Challenge

There are currently multiple initiatives to research a vaccine to control this world pandemic and eradicate this threat. However, we need to prevent the spread of the disease using popular means of communication, such as virtual tools that can allow us to give feedback on human behavior in past similar situations. Past pandemics have taught us that social distancing is the best way to prevent the spread, so we must try to keep ourselves safe in our homes by a quarantine.

We decided to learn through experimenting and building things during COVID19 lockdown. Our project brings together our interests in data science, coding, machine learning, and IOT in a casual way.

We built a model using Arduino with sensors: to document changes happening in our immediate environment like heavy rainfall, floods, Analyzing the data gathered by our sensors, we were able to better appreciate the gradual changes happening around us because of the lockdown.

We did not want to lose our coding skills so we ended up writing Python programs, machine learning algorithms to analyze and create graphs of data being gathered from the NASA Space App challenge resources like JAXA global rainfall watch, climate watch.

How We Developed This Project

Machine Learning Algorithms:

In my project, we have used machine learning algorithms such as linear regression/logistic regression, support vector machine (SVM), matplotlib for plotting the graphs.

3.1.1. Linear/Logistic Regression

Linear regression is used to determine or identify the relationships between two columns/variables in a dataset. Logistic regression is used for analyzing a dataset that has one independent variable or more. The results obtained from analyzing the variables is either 0s or 1s/true or false.

3.1.2. Support Vector Machine (svm): It is used for classification between any set of groups present in the dataset. The objective of the SVM is to draw the best fit line which is used to differentiate between two different classes or groups present in the dataset.

3.1.3. Matplot lib

It is the library that can be used for creating visualization by plotting graphs where we can differentiate the rainfall rate based on states when the rain occurs & further differentiates the quantity of the rainfall of each city each month.

3.2 Hardware Modules

The required hardware modules are the sensors, microcontrollers and the materials for the power supply. The objective of these hardware components is to control and measure the pressure of water. It collects the data on water level and the information is stored in the cloud through the communication of WIFI and the data is being enabled to pass the information through the internet.

3.2.1 Microcontroller

The microcontroller helps in processing the information which is being fetched from the sensors and this information is being sent to the admin through the medium of the cloud.

3.2.2 Sensors

The sensors which help to give the information to the microcontroller from various nodes located at a different place. The sensors that are required for this project are as follows:

*The ultrasonic sensor-This sensor is used to measure the level of the water and the average rainfall that is being occurred at a particular place. If water level strikes at a particular level it emits very high frequency so these echo signals are reflected in the sensors and it gives an alert message to the microcontroller and sends the information to the cloud. The ultrasonic sensor consists of 4-pin. The 4-pins are used to measure water level, trigger, ground connection & the last current.

*Pressure sensor - BMP Barometric sensor is used to identify the atmospheric pressure present inside the water.

*Humidity sensor - DHT11 sensor works on the principle of one wire protocol which identifies the climatic changes and the humidity which gives us the output in a digital format.

3.2.3 Power Supply

The high energy of power supply is not needed, so the current we get in the AC power supply is being converted to the DC power supply and it can be used in the implementation.

3. Database Module

The values that are being fetched by the microcontrollers from the sensors are sent to the cloud via WIFI. The cloud will have access to all registered users. This stored data is being redirected to the websites where the users can access the information about the condition of the flood occurring.

How We Used Space Agency Data in This Project

We love Astronomy, after watching the NASA Space Apps Bootcamp videos we came to know about NASA resources like JAXA real time rainfall watch and jaxa earth data collection by satellites. And that data which can observe heavy weather forecasting rainfall,GSMap climate,precip forecasts,RIKEN nowcast, . The Data was also available on NASA Worldview portal in real-time. We used these datasets and compare tools available on the NASA website to assess change in" climate,weather,rainfall,hazards "during the lockdown period.

It is the model solution for predicting the hazards challenges imposed in a simple application and a complete information platform where we approach these issues, we collect information from different sources, like the Rainfall global watch, International demographic, weather databases and the official rainfall data of each government.

India has faced many natural disasters. Due to the floods, it causes heavy damages to properties, wild life’s and huge loss of human lives. This problem can be overcome by a proper flood monitoring system integrated with Machine Learning and IoT by using resources from the NASA Space APP challenge and the proposed system can be used for better monitoring of water levels in dams. If the flood occurs, it easily communicates the information to the nearby people. The implemented communication systems and transmission technologies are more efficient and can easily adapt to the background technologies. The proposed methodology has increased efficiency and accuracy for the prediction of floods, and even it gives good efficiency at critical conditions. Overall this proposed system would be advantageous for the people to get enough time to evacuate from the flood-prone areas before the flood occurs.