Kc and Ky Data for Irrigated Wheat in Southern Ethiopia
Domain:
agricultureRecord type:
dataset
Creator:
EbsdagWen
Publisher:
fig
Host:
This dataset supports the study titled “Machine Learning and Experimental Modeling of Crop Coefficient and Yield Response Factor for Lowland Irrigated Wheat in Southern Ethiopia.” It includes field measurements and derived variables used for modeling wheat crop coefficient (Kc) and yield response factor (Ky) under different irrigation and environmental conditions.Dataset Contents:Climatic and agronomic parameters:Soil moisture (%)Rainfall (mm)Reference evapotranspiration (ETo, mm/day)Actual evapotranspiration (ETc, mm/day)Yield (kg/ha)Applied irrigation depth and frequencyMethodology:
Data were collected through experimental field trials and supplemented by remote sensing observations. Machine learning models (e.g., Random Forest, Linear Regression, k-Nearest Neighbors) were trained and validated to predict crop coefficient and yield response under varying environmental and irrigation treatments. Preprocessing included imputation of missing data, outlier removal using IQR, and feature selection.Data Format:Accompanying metadata file (.txt or .xlsx)Data dictionary with variable definitions and unitsThis dataset is valuable for researchers in agronomy, irrigation engineering, and precision agriculture, especially those exploring data-driven crop modeling and sustainable water management in arid and semi-arid regions.
Data were collected through experimental field trials and supplemented by remote sensing observations. Machine learning models (e.g., Random Forest, Linear Regression, k-Nearest Neighbors) were trained and validated to predict crop coefficient and yield response under varying environmental and irrigation treatments. Preprocessing included imputation of missing data, outlier removal using IQR, and feature selection.Data Format:Accompanying metadata file (.txt or .xlsx)Data dictionary with variable definitions and unitsThis dataset is valuable for researchers in agronomy, irrigation engineering, and precision agriculture, especially those exploring data-driven crop modeling and sustainable water management in arid and semi-arid regions.