VEGG

https://www.canva.com/design/DAErzlRkrCk/nPpiz9MOEBT28UWThV5RXw/view?utm_content=DAErzlRkrCk&utm_campaign=designshare&utm_medium=link&utm_source=publishsharelink

https://github.com/edvardas-vabuolas/-Flutter-NASA-Sunshine-Hackathon

https://github.com/edvardas-vabuolas/-Flutter-NASA-Sunshine-Hackathon

https://github.com/edvardas-vabuolas/NASA-Sunshine-Hackathon

The app provide useful information from NASA database and recommend the most suitable plants in the chosen area.

Here are two sections: the top one contains an analysis on energy, temperature, humidity and soil wetness, based on the location you indicated at the start and time resolution you told us at a later screen. Note that the x-axis is for every data entry you requested (f.e. 'hourly' and 'last week') and y-axis is for one of the four variables. We also calculated an average value so you would not have to.

The second section contains a database of plants that is sorted based on the goodness of fit. What we mean by that, is that we look at the sunlight (in ft-c units), temperature (C), humidity (%) and soil wetness (%) and do some comparison against the preferred plant's growth conditions. The ones that match best are at the top, whilst the least suggested are at the bottom.

In this way, the businesses will explore suggested plants and minimise costs, maximise production and efficiency by cultivating the most suitable plants. The goverment could design green spaces, plan efficient urban gardens, maintain native flora, plant sustainable forests. Households will learn about the local flora, grow the most suitable plants and share the harvest with local community.

For the backend we used: API requests towards NASA Power, data processing, data categorising, and endpoint creation for frontend - we used Python 3.9 and 5 related libraries: Pandas, Flask, JSON, Requests and Datetime. We used Amazon Web Services to run Python WSGI server. Tunnel is created using Ngrok.io web services (custom sub-domain: sunshine-hackathon.eu.ngrok.io). In terms of hardware for backend processing, AWS server runs on Windows 2019 OS, 2GB RAM memory, 1 vCPU and 2TB SSD. 

For the frontend - UI interface creation, data visualization and API requests towards backend AWS server - we used Flutter 2.5 and several Google Developers Console APIs:

• Geocoding API
• Geolocation API
• Maps Javascript API
• Maps SDK for Android
• Maps SDK for iOS
• Maps Static API
• Places API

We used data from NASA’s Prediction of Worldwide renewable Energy Resources (POWER) web services portal: all sky surface shortwave downward sunlight, temperature of 2 meters, relative humidity of 2 meters, roots soil wetness (they are essential factors for plant growth) to predict the best conditions for the plant growth. It is very useful for predicting new agriculture patterns that are altering due to climate change. We used the categorization of plant growing conditions from the article "Growing indoor plants with success” by Bodie V. Pennisi and we want to expand this categorization with soil pH, nutrients and relief.

It was a great experience to gain the skills of creating the app and managing the work of our team. We are inspired how many data of the climate and soil NASA have. It can be used not only for the alternative energy, but also for the most important business in the world - agriculture. We are concerned that due to climate change agriculture patterns are altering so fast and it leads to the food insecurity. This app could help track the conditions for growing the plants. One of the challenges for our team was to find the database of the plants and their growing conditions. We think to

www.climatexchange.org.uk “Impacts, Adaptation and Vulnerability”, Caroline Holmes, 2015

https://extension.uga.edu “Growing indoor plants with success”, Bodie V. Pennisi

https://www.futurelearn.com/ “Impact of climate change on agriculture”, University of Reading

#agriculture #climatechange #climate #sunlight

This project has been submitted for consideration during the Judging process.