Early stage | Forestry & Forest Products | SDG13 | Zambia

Reducing carbon emissions in Zambias forest using compute vision.

Share this post

1. General

Category

SDG 13: Climate Action

Category

Forestry & Forest Products

2. Project Details

Company or Institution

Zamculture

Project

Reducing carbon emissions in Zambias forest using compute vision.

General description of the AI solution

Our project is based on detecting and reducing carbon emission in forest using compute vision .We intended to collect data using satellite and also data scientist, machine learning and artificial intelligence.After collecting the data we are going to preprocess it , and it will be ready for training and metrics and performance evaluation using keras software for analysis.
The impact of this project is for about 300 people within and near the ,national parks near the forest that will benefit from this project.

Website

https://github.com/Zamculture

Organisation

Zamculture

3. Aspects

Excellence and Scientific Quality: Please detail the improvements made by the nominee or the nominees’ team or yourself if your applying for the award, and why they have been a success.

Type of AI
In this project we are using a combination of technologies such as Computer vision and deep learning through satellite imagery and drones with which we collect data , which we preprocess and vectorise from image pixel to data that is then arranged and trained using Keras and evaluating the performance.Some of the people we work with include data scientist, Machine learning and artificial intelligence engineers.
Compared to what Zambia has been modelling forests , we have come up with more innovative and modern ways of reducing carbon through artificial intelligence which our country could not do before and this makes it quick, effective efficiency and more innovative.This is an artitificial intelligence application under detection using computer vision which we can not do accurately with our natural eyes.
Quality of AI solutions and Algorithms
We have decided to use convolutional neural networks which work best for image data in order to train the models better.
Describe status of technology.
We are still operating locally but we are consider cloud use especially as we collect more data, we intend to use AWS infrastrature to make this project more efficient and effective as it is very important to solving the climate change problem by reducing emissions.However for those that want to collaborate and contribute to our work we are already on github account.

Scaling of impact to SDGs: Please detail how many citizens/communities and/or researchers/businesses this has had or can have a positive impact on, including particular groups where applicable and to what extent.

This project has got an impact on the surrounding communities of people bout 300 and and animal parks that depend on it. It will have a positive impact in that the carbon emissions will be reduced with the help of computer vision technologies and the data being collected .Hence this project replies positively to objectives and the scope of sustainable development goals with AI technologies.This has also helped to begin to develop a dataset in line with climate change and the forest in zambia. We hope to measure the progress of this project at each level and mile stone and do both baseline, mid , and end evaluation.
This project intends to use computer vision ,deep learning and satellite imagery technologies to reduce carbon emissions in forests and this will trigger further research as we will be on github account so that other research bodies can contribute and we also hope to publish scientific papers and artiicals to further the body of knowledge in the field of Climate change and forests.this will encourage research, start ups,public and corporates to also benefit from the project.
We hope to enhance the use of artificial intelligence in climate change and SDGs in Africa in order to get homegrown solutions with acceralation due to technologies such as computer vision and satellite.

Scaling of AI solution: Please detail what proof of concept or implementations can you show now in terms of its efficacy and how the solution can be scaled to provide a global impact ad how realistic that scaling is.

We do have a prototype that we have developed on AI for climate in our Zambian forest.However we ve began rolling out our project by first collecting data.We have not scaled up completely due to lack of funding.We hope to advance by using the cloud computing solutions such as AWS for deep learning Our organisation Zamculture works around Artificial intelligence to acceralate solutions to various SDG problems ranging from energy, climate ,poverty ,agriculture and education hence we hope to increase and expand these technologies to other organisation especially start ups that also want to engage in the same line of business as us , we will also grant them the support.This will increase the use of AI for SDGs solutions in the region.We also hope to engage our communities schools,university and municipality so as increase on the awareness .
we hope to write journal papers and publications on reduction of carbon emissions from forests using AI, and also we already working on including this project to our existing github account so that we can make it open source for more collaboration and contributions from university researchers, forest department . We shall also contribute to datasets especially for machine learning,artificial intelligence and forests.

Ethical aspect: Please detail the way the solution addresses any of the main ethical aspects, including trustworthiness, bias, gender issues, etc.

Ethical consideration have been taken into consideration as we carry out this project using computer vision .At every level of the project we garant peoples freedoms by not collecting biodata and meta data without there consent.We have also considered making the project process trust worthy through wide public consultation before we could embark on the project .We have engaged community,municipality and government leaders on board.
we have also made sure that we reduce on basis therefore we ve made the project very inclusive by giving leading positions to women and the disadvantaged in the societies that are affected.

CONTACT

International Research Centre in Artificial Intelligence
under the auspices of UNESCO (IRCAI)

Jožef Stefan Institute
Jamova cesta 39
SI-1000 Ljubljana

info@ircai.org

ircai.org

FOLLOW US

The designations employed and the presentation of material throughout this website do not imply the expression of any opinion whatsoever on the part of UNESCO concerning the legal status of any country, territory, city or area of its authorities, or concerning the delimitation of its frontiers or boundaries.

Design by Ana Fabjan