County level maize yield estimation using artificial neural network
- PDF / 2,524,773 Bytes
- 8 Pages / 595.276 x 790.866 pts Page_size
- 40 Downloads / 230 Views
REVIEW ARTICLE
County level maize yield estimation using artificial neural network Joshua Irungu Mwaura1 · Benson Kipkemboi Kenduiywo 1,2 Received: 27 April 2020 / Accepted: 13 August 2020 © Springer Nature Switzerland AG 2020
Abstract Maize yield estimates are useful for county food security preparedness. Techniques such as regression and simulation have been used by various studies to model and predict maize yield. This study used a feed-forward, back propagation artificial neural network with levenberg-marquardt algorithm for training. Artificial neural networks framework was chosen because its a data driven method that is relatively less widely used in county level yield prediction. Moreover, neural networks has key merits, such as require less formal statistical training, ability to detect nonlinear relationships by identifying likely interactions between variables and the availability of multiple training algorithms. We modelled historical maize yield between 2005–2016 as function of satellite derived precipitation, temperature, reference crop evapotranspiration, soil moisture and normalized difference vegetation index (NDVI) to predict maize yields at pixel level. The data were obtained with a spatial resolution of ≈ 4 km and subsequently, the predictions was done at ≈ 4 km pixel size. The historical reference maize yield data was divided into two sets for model training and validation. The model predicted maize yield with R2 and root mean square error of 0.76 and 0.038 MT/ha in Trans-Nzoia county and 0.86 and 0.016 MT/ha, respectively, in Nakuru county. These findings shows a promising future for applications targeting to rapidly assess county level food preparedness in Kenya because maize is a major staple food. Keywords Boruta algorithm · Artificial neural networks · Machine learning · Maize yield prediction · Modeling · Remote sensing
Introduction There is a linear growth in world population according to data and projections published by United Nations. This data also gives 1.18% as the current world’s population growth per year, which approximates to annual population increment of 83 million people (United Nations 2015). More than half of global population growth between now and 2050 is expected to occur in Africa. Africa has the highest rate of population growth among major areas, growing at a pace of 2.55% annually in 2010–2015. Consequently, of the additional 2.4 billion people projected to be added to the global population between 2015 and 2050, 1.3 billion will be from * Joshua Irungu Mwaura [email protected] 1
Department of Geomatic Engineering and Geospatial Information Systems, Jomo Kenyatta University of Agriculture and Technology, Nairobi, Kenya
Environmental Science and Policy, University of California, Davis, USA
2
Africa (United Nations 2015). This growth in population will directly impact food supply systems. Africa relies heavily on weather dependant agriculture. It also experiences short-term changes in climate (Stige et al. 2006). These two factors increases stress on
Data Loading...
