Abstract
As sugarcane matures, its sucrose content increases, but delaying harvest too long can increase production costs and lead to financial losses. The metahara sugar factory currently relies on traditional harvesting methods based on field conditions. This study aims to develop a decision support tool to optimize the harvesting schedule of the factory. Historical data from 2010/11 to 2019/20 were analyzed, with a focus on crop variety, maturity, and soil fertility, to create predictive models via ordinary least squares. Most models showed statistical significance, with adjustments made for climatic factors. Forecasting was conducted for 1,199 fields over nine months and integrated into a Harvest Schedule Mixed Integer Linear Programming model. The optimized schedule recommended changing the harvest month for 804 fields (67.06% of the total), potentially increasing net returns by 15.28% while meeting all constraints. Additionally, the average theoretical recoverable sugar content was improved by 1.23%.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by-nc-nd. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 3
Claim · model-written summary
The optimized harvest schedule could potentially increase net returns by 15.28%
Verbatim
t0“Maximizing economic returns from sugarcane production”
t1“Metahara sugar factory, Ethiopia”
e1“potentially increasing net returns by 15.28%”
Claim · model-written summary
The optimized schedule improved the average theoretical recoverable sugar content of sugarcane by 1.23%
Verbatim
t0“Maximizing economic returns from sugarcane production”
e2“the average theoretical recoverable sugar content was improved by 1.23%”
Claim · model-written summary
The optimized schedule recommended changing the harvest month for 804 fields (67.06% of the total)
Verbatim
t0“Maximizing economic returns from sugarcane production”
e3“The optimized schedule recommended changing the harvest month for 804 fields (67.06% of the total)”