folder_zip
Olisah, Chollette and Smith, Lyndon and Smith, Melvyn and Lawrence, Morolake and Ojukwu, Osita (2023) Corn yield prediction model with deep neural networks for smallholder farmer decision support system. UWE https://researchdata.uwe.ac.uk/id/eprint/687/
Brief summary of project
This data comprises of raw and processed environmental data, climate, weather and cultivation area, for corn yield prediction in Sub-Sahara Africa, with emphasis in Nigeria. The data was collected for predicting crop yield with the sole purpose of designing a decision support system to help smallholder farmers to determine how the conditions at a given farm will affect yield positively or negatively. However, the data can serve several other purposes via analysis, interpretation or defining food security and policy design. Therefore, researchers are welcome to use the data as they deem fit, but we request that the original work for which the data was collected and used be cited.
| Uncontrolled Keywords: | Crop Yield, Corn Yield, Africa, Nigeria districts, Soil data, Climate Data, Cultivation Area data, Crop yield data, corn yield prediction. |
|---|---|
| UWE College/School: | College of Arts, Technology and Environment > School of Engineering |
| Creators: | Olisah, Chollette and Smith, Lyndon and Smith, Melvyn and Lawrence, Morolake and Ojukwu, Osita |
| URI: | https://researchdata.uwe.ac.uk/id/eprint/687 |
| Data collection method: | Nigeria [9.0820° N, 8.6753° E] is located on the west coast of Africa and has an arable land area of 34 million hectares. There are 36 states in Nigeria with about 214 and 10 as the most and least number of districts per state. The environmental data collected for each state are described as follows. Grid map climate data which comprised eight (8) environmental variables, namely: average temperature C^0, minimum temperature C^0, maximum temperature C^0, precipitation (mm), solar radiation (kJ m^(-2) day^(-1)), wind speed (m s^(-1)), and water vapor (kPa) taken at 30 seconds (s), 2.5 minutes (m), 5 m, and 10 m high spatial resolutions of ~1 km2 to ~340 km2 were obtained from WorldClim global climate database [https://www.worldclim.org/data/index.html]. The data is per grid point on the map and recorded monthly from January to December of each year between 1970 to 2000. The yearly corn yield was computed for 1000 metric tonnes for a 1000 hectares cultivation area and spans from 1995 to 2006. These data were obtained from a data repository managed by Kneoma Corporation [https://knoema.com/data/nigeria+agriculture-indicators-production+maize?unit=]. Grid map soil data of 250 minutes spatial resolution were retrieved from AfSIS [https://www.isric.org/projects/soil-property-maps-africa-250-m-resolution ]. It includes wet soil bulk density, dry bulk density (kg dm-3), clay percentage of plant available water content, hydraulic conductivity, the upper limit of plant available water content, the lower limit of, organic matter percentage, pH, sand percentage (g 100 g-1), silt percentage (g 100 g-1) and, clay percentage (g 100 g-1), and saturated volumetric water content variables measured at depths 0–5, 5–10, 10–15, 15–30, 30–45, 45–60, 60–80, 80–100, and 100–120 measured in centimetres (cm). The soil data span is from 1960 to 2012. The Geolocation coordinates (latitude and longitude) of each state were obtained from Google Maps. Then used to extract the point values from the grid maps of each environmental variable (climate and soil) at specific district locations of the 36 states in Nigeria using the Esri-ArcGIS professional 2.5 software tool. |
| Geographic coverage: | Nigeria |
| Resource language: | English |
Data
Explore Further
Read more research from the creator(s):
- Olisah, Chollette
- Smith, Lyndon
- Smith, Melvyn
- Lawrence, Morolake
- Ojukwu, Osita
Read publications using this data:
Actions (Log-in required)
View Item