Delineating site-specific management zones for precision agriculture

Abstract

SUMMARYDelineating site-specific management zones within fields can be helpful in addressing spatial variability effects for adopting precision farming practices. A 3-year (2008/09 to 2010/11) field study was conducted at the Postgraduate Agricultural Research Station, University of Agriculture, Faisalabad, Pakistan, to identify the most important soil and landscape attributes influencing wheat grain yield, which can be used for delineating management zones. A total of 48 soil samples were collected from the top 300 mm of soil in 8-ha experimental field divided into regular grids of 24 × 67 m prior to sowing wheat. Soil and landscape attributes such as elevation, % of sand, silt and clay by volume, soil electrical conductivity (EC), pH, soil nitrogen (N) and soil phosphorus (P) were included in the analysis. Artificial neural network (ANN) analysis showed that % sand, % clay, elevation, soil N and soil EC were important variables for delineating management zones. Different management zone schemes ranging from three to six were developed and evaluated based on performance indicators using Management Zone Analyst (MZA V0·1) software. The fuzziness performance index (FPI) and normalized classification entropy NCE indices showed minimum values for a four management zone scheme, indicating its appropriateness for the experimental field. The coefficient of variation values of soil and landscape attributes decreased for each management zone within the four management zone scheme compared to the entire field, which showed improved homogeneity. The evaluation of the four management zone scheme using normalized wheat grain yield data showed distinct means for each management zone, verifying spatial variability effects and the need for its management. The results indicated that the approach based on ANN and MZA software analysis can be helpful in delineating management zones within the field, to promote precision farming practices effectively.

Assessing wheat spatial variation based on proximal and remote spectral vegetation indices and soil properties

“…It is a sounder approach not to use crop yield in homogeneous area delineation, as yield is a grower's ultimate goal and cannot be predicted months before harvesting. This choice is supported by other sources in the literature (Peralta et al, 2015;Farid et al, 2016).…”

“…Lastly, adoption of more than three levels for both homogeneous areas and GY is seldom echoed in the literature on wheat (Farid et al, 2016). Our decision to stop at three, beside limiting field patchiness to the benefit of simpler crop practices (Paice et al, 1998), is supported by the fact that choosing more than three levels was shown to provide modest advantages in the amount of explained variance (Fraisse et al, 2001;Tagarakis et al, 2013).…”

Identification of the most limiting factor for rice yield using soil data collected before planting and during the reproductive stage

“…During the process of identifying the most limiting factor influencing crop yield, researchers often select the initial soil parameters measured before crop planting as the explanatory soil variables (Asadu et al, ; Casanova et al, ; Farid et al, ; Simmonds et al, ; Zheng et al, , ). However, soil properties during sensitive stages of crop growth, such as the reproductive stage, may have a greater effect on crop yield than have soil properties during other growth stages (Fageria, ; Rao, Mishra, Gupta, & Rathore, ).…”

“…Appropriate statistical tools, such as multiple linear regression (e.g., Asadu, Dixon, & Okechukwu, 2002), principal component analysis (e.g., Jagadamma, Lal, Hoeft, Nafziger, & Adee, 2008), artificial neural networks (Farid, Bakhsh, Ahmad, Ahmad, & Mahmood-khan, 2016;Miao, Mulla, & Robert, 2006), ridge regression (Nuttall, Armstrong, & Connor, 2003), and the boundary line method (Casanova, Goudriaan, Bouma, & Epema, 1999), can play important roles in identifying the most limiting factor influencing the crop yield. As an inherently nonparametric modeling approach, classification and regression trees (CARTs) can effectively deal with large data sets and issues of higher dimensionality.…”

Site-Specific Aquifer Characterization and Identification of Potential Groundwater Areas in Pakistan

“…Kriging is most suitable interpolation technique and has many advantages over the others as reported in literature. Such an approach has been recommended and used by many other researchers [33][34][35][36]. Kumar and Remadevi [37] compared the Inverse Squire Distance (ISD) and kriging interpolation techniques for the spatial analysis of groundwater levels and reported that the ISD method resulted in higher error as compared to the kriging method.…”