Assessment of the Use of Geographically Weighted Regression for Analysis of Large On-Farm Experiments and Implications for Practical Application

Evans, F.; Recalde-Salas, Angela; Rakshit, S.; Scanlan, Craig; Cook, Simon

doi:10.3390/agronomy10111720

Cited by 24 publications

(16 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, a linear function was assumed in order to simplify the yield simulation process as implemented by Evans et al. (2020) and Trevisan et al. (2020).…”

Section: Methodsmentioning

confidence: 99%

“…However, the importance of these terms depends on the range of the rates explored and the variability of soil and weather conditions. In this study, a linear function was assumed in order to simplify the yield simulation process as implemented by Evans et al (2020) and Trevisan et al (2020). First, the spatial distribution of each regression coefficients of Equation 1 was simulated independently by an unconditional Gaussian geostatistical simulation procedure (Webster & Oliver, 2007).…”

Section: Yield Data Simulation Procedures and Model Assumptionsmentioning

confidence: 99%

See 1 more Smart Citation

Design of on‐farm precision experiments to estimate site‐specific crop responses

et al. 2021

View full text Add to dashboard Cite

Site-specific prescriptions require estimating response functions to controllable inputs across the field. The methodology of applying geographically weighted regression to on-farm precision experimentation studies opens new opportunities to study site-specific responses to inputs in farmers' fields by locally estimating the regression coefficients. However, the effect of the experiment's spatial layout, such as plot dimensions and randomization, and spatial structure of the yield response on the experiment performance are yet to be studied. Detailed information about these effects is needed to improve trial design to detect site-specific responses. A simulation study was conducted using 14,400 fields of 37 ha and 9-m resolution. Coefficients from a spatial variable response function were drawn from five random fields generated by unconditional Gaussian geostatistical simulations. Four levels of nitrogen were assigned to plots using 18 systematic and randomized chessboard designs with different plot sizes. Simulated yield data was obtained by combining the coefficients, treatment, and random error. The effect of spatial structure and the designs was assessed with measures of agreement between the true and estimated maps of regression coefficients. The ability to capture or approximate the true spatial pattern of the response function increased as the underlying response function's spatial structure increases. Overall differences in performance between design were observed across the spatial structure tested, mostly related to randomization and plot dimensions. In general best results were achieved by systematic designs with small or intermediate plot sizes (r = 0.54 ± 0.05, MAE = 0.005 ± 0.0005, SDR = 0.81 ± 0.06, and CP = 0.50 ± 0.04). Our methodology provides a path for testing designs under different spatial variability scenarios.

show abstract

“…In this study, a linear function was assumed in order to simplify the yield simulation process as implemented by Evans et al. (2020) and Trevisan et al. (2020).…”

Section: Methodsmentioning

confidence: 99%

Section: Yield Data Simulation Procedures and Model Assumptionsmentioning

confidence: 99%

Design of on‐farm precision experiments to estimate site‐specific crop responses

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Alternatively, Rakshit et al (2020) adapted a local regression approach, called geographically weighted regression (GWR), to obtain spatially-varying estimates of treatment effects for OFE. Additionally, Evans et al (2020) conclude that, through simulation studies, GWR is a simple method for the analysis of OFE data and is able to accurately separate yield variation that is not due to the applied treatment from yield response due to treatment. The limitation in the study is that they used a randomised design and assumed a linear response to fertiliser treatment.…”

Section: Introductionmentioning

confidence: 95%

“…OFE enables farmers the flexibility to implement large-scale experiments in order to test management practices on their farms (Evans et al 2020). The aim of OFE is to enable farmers to improve their competence of uncertainties and to take into account their existing strengths of handling translational and structural uncertainty (Cook et al 2013).…”

Section: Introductionmentioning

confidence: 99%

Optimal design for on-farm strip trials -- systematic or randomised?

Cao¹,

Grose²,

Brown³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

There is no doubt on the importance of randomisation in agricultural experiments by agronomists and biometricians. Even when agronomists extend the experimentation from small trials to large on-farm trials, randomised designs predominate over systematic designs. However, the situation may change depending on the objective of the on-farm experiments (OFE). If the goal of OFE is obtaining a smooth map showing the optimal level of a controllable input across a grid made by rows and columns covering the whole field, a systematic design should be preferred over a randomised design in terms of robustness and reliability. With the novel geographically weighted regression (GWR) for OFE and simulation studies, we conclude that, for large OFE strip trials, the difference between randomised designs and systematic designs are not significant if a linear model of treatments is fitted or if spatial variation is not taken into account. But for a quadratic model, systematic designs are superior to randomised designs.

show abstract

“…Geographically weighted regression (GWR) is a spatially local regression technology [19]. This model takes the spatial coordinates into the coefficient estimation, permitting the coefficients to vary with spatial position.…”

Section: Introductionmentioning

confidence: 99%

An Integrated Yield-Based Methodology for Improving Soil Nutrient Management at a Regional Scale

JinFen

et al. 2022

Agronomy

View full text Add to dashboard Cite

The relationships between crop yield and its selected related impact factors has often been explored using ordinary least squares regression (OLSR). However, this model is non-spatial and non-robust. This study first used stepwise regression to identify the main factors affecting winter wheat yield from twelve potential related factors in Yucheng County, China. Next, robust geographically weighted regression (RGWR) was used to explore the spatially non-stationary relationships between wheat yield and its main impact factors. Then, its modeling effect was compared with that of GWR and OLSR. Last, robust geostatistical analysis was conducted for spatial soil management measures in low-yield areas. Results showed that: (i) three main impact factors on wheat yield were identified by stepwise regression, namely soil organic matter, soil total phosphorus, and pH; (ii) the spatially non-stationary effects of the main impact factors on wheat yield were revealed by RGWR but were ignored by OLSR; (iii) RGWR obtained the best modeling effect (RI = 52.31%); (iv) robust geostatistics obtains a better spatial prediction effect and the low-yield areas are mainly located in the northeast and the middle east of the study area. Therefore, the integrated yield-based methodology effectively improves soil nutrient management at a regional scale.

show abstract

Assessment of the Use of Geographically Weighted Regression for Analysis of Large On-Farm Experiments and Implications for Practical Application

Cited by 24 publications

References 62 publications

Design of on‐farm precision experiments to estimate site‐specific crop responses

Design of on‐farm precision experiments to estimate site‐specific crop responses

Optimal design for on-farm strip trials -- systematic or randomised?

An Integrated Yield-Based Methodology for Improving Soil Nutrient Management at a Regional Scale

Contact Info

Product

Resources

About