Optimizing Energy Demand in Rural Communities via Precision Agriculture Technology (SWIFT)

Details

 PROJECT SUMMARY

Project name

Optimising Energy Demand in Rural Communities via Precision AgricultureTechnology (SWIFT)

AMU project code

EXT/UK/TH04/AMIT/RETRC/04/2015

Project short-name

OEDiRC

Project phase

I

Partner(s)/ country(ies)

UK

AMU coordinating office(s)

Renewable Energy Technology Research Center

Project type

Research

Project location

Minan Abaya rural village in Daramalo woreda, Gamo zone, SNNPR, Ethiopia

Target communities

Rural communities in the Minan Abaya catchment

Project coordinator

Beyene Feye Fulasa (AMU side)

Principal investigator

Lensa Jotte

Co-investigators (if any)

Kelly Crowther-Riley, Jenna Ross, Ed Mallows, and Beyene Feye Fulasa

AMU budget contribution ( )

8,050

Total project budget ( )

32,199

Total project budget ( )

40,249

Project start

1-Apr-23

Project end

31-Mar-24

Progress reporting period

Quarterly

Financial reporting period

Quarterly

Contact person

Beyene Feye Fulasa (This email address is being protected from spambots. You need JavaScript enabled to view it.)

Project Management Office

Office of the Director for Grant and Collaborative Project Management:
Dr. Thomas Torora (This email address is being protected from spambots. You need JavaScript enabled to view it.; This email address is being protected from spambots. You need JavaScript enabled to view it.)

PROJECT DESCRIPTION

One of the challenges of providing electricity to rural communities estimating the energy demand that is mainly associated with irrigation. For mini-grid developers and renewable energy providers, having accurate demand forecasting technology is very critical to avoid under or over-investments. This project focuses on estimating energy demand for small-scale hydro-power and solar mini-grids that would power water pumps in rural areas by utilizing SWIFT (Soil Water Index Forecast Technology). SWIFT is developed by modeling a combination of satellite, climate, and static data to predict soil moisture concentration at different soil depths. Moreover, the sites under study in Daramalo woreda in Gamo zone, SNNPR, Ethiopia are currently irrigating their land from ground or surface water using diesel pumps. Transitioning from diesel to electric pumps would save farmers money (as their OPEX would go down), increase productivity and reduce carbon emissions. To this end;

1) Innovative Solution: The project will upscale the intelligence level of SWIFT via machine learning and the application of satellite data to clearly inform the user about the farm plot's historical and future irrigation needs based on crop types which will then be mapped onto the energy demand to assess and design the appropriate alternative source of renewable energy

2) The project will use SWIFT to identify/estimate the size and location of farmlands that have been irrigated for the past 7 years by using satellite data with the aim of providing historical context to energy providers and mini-grid developers about energy demand evolution.

3) The project will conduct spatial and temporal analysis of diesel pumps' CO2 contribution to make a case for the transition to electric pumps.

4) The outcome of this project will be presented to local stakeholders (farmers, local governmental bodies, mini-grid developing investors, R&D community) and also to countries like Kenya, Ghana, and Malawi.