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

Agronomy ◽  
2020 ◽  
Vol 10 (11) ◽  
pp. 1720
Author(s):  
Fiona H. Evans ◽  
Angela Recalde Salas ◽  
Suman Rakshit ◽  
Craig A. Scanlan ◽  
Simon E. Cook
Keyword(s):  
Spatial Variation ◽  
Geographically Weighted Regression ◽  
Large Scale ◽  
Treatment Effects ◽  
Management Practices ◽  
Response To Treatment ◽  
Weighted Regression ◽  
Yield Response ◽  
Practical Application ◽  
On Farm

On-farm experimentation (OFE) is a farmer-centric process that can enhance the adoption of digital agriculture technologies and improve farm profitability and sustainability. Farmers work with consultants or researchers to design and implement experiments using their own machinery to test management practices at the field or farm scale. Analysis of data from OFE is challenging because of the large spatial variation influenced by spatial autocorrelation that is not due to the treatment being tested and is often much larger than treatment effects. In addition, the relationship between treatment and yield response may also vary spatially. We investigate the use of geographically weighted regression (GWR) for analysis of data from large on-farm experiments. GWR estimates local regressions, where data are weighted by distance from the site using a distance-decay kernel. It is a simple approach that can be easily explained to farmers and their agronomic advisors. We use simulated data to test the ability of GWR to separate yield variation due to treatment from any underlying spatial variation in yield that is not due to treatment; show that GWR kernel bandwidth can be based on experimental design to accurately separate the underlying spatial variability from treatment effects; and demonstrate a step-wise model selection approach to determine when the response to treatment is global across the experiment or locally varying. We demonstrate our recommended approach on two large-scale experiments conducted on farms in Western Australia to investigate grain yield response to potassium fertiliser. We discuss the implications of our results for routine practical application to OFE and conclude that GWR has potential for wide application in a semi-automated manner to analyse OFE data, improve farm decision-making, and enhance the adoption of digital technologies.

Modeling the Spatial Variation in U.S. Airfares Utilizing Geographically Weighted Regression

2014 ◽  
Vol 5 (4) ◽  
pp. 54-71
Author(s):  
Hilton A. Cordoba ◽  
Russell L. Ivy
Keyword(s):  
Spatial Variation ◽  
Influencing Factors ◽  
Geographically Weighted Regression ◽  
Regression Models ◽  
Yield Management ◽  
Weighted Regression ◽  
Local Models ◽  
Multivariate Approach ◽  
Global Models ◽  
Economic Changes

Modeling airline fares is quite challenging due to the constantly changing fare structure of the airlines in response to competitors, yield management principles, and a variety of political and economic changes, and has become more complex since deregulation. This paper attempts to add to the literature by providing a more in-depth look at fare structure using a multivariate approach. A total 6,200 routes between 80 primary U.S. airports are analyzed using linear and geographically weighted regression models. The results from the global models reinforce some of the expectations mentioned in the literature, while the local models provide an opportunity to analyze the spatial variation of influencing factors and predictability.

scholarly journals Assessing spatial variation of PM2.5 and NO2 across Europe using Geographically Weighted Regression

2019 ◽  
Vol 3 ◽  
pp. 65
Author(s):  
Chen J ◽  
de Hoogh K ◽  
van Donkelaar A ◽  
Ketzel M ◽  
Hertel O ◽  
...  
Keyword(s):  
Spatial Variation ◽  
Geographically Weighted Regression ◽  
Weighted Regression

scholarly journals A CUDA-Based Parallel Geographically Weighted Regression for Large-Scale Geographic Data

2020 ◽  
Vol 9 (11) ◽  
pp. 653
Author(s):  
Dongchao Wang ◽  
Yi Yang ◽  
Agen Qiu ◽  
Xiaochen Kang ◽  
Jiakuan Han ◽  
...  
Keyword(s):  
Geographically Weighted Regression ◽  
Large Scale ◽  
Parallel Architecture ◽  
Weighted Regression ◽  
Geographic Data ◽  
Distance Weighted ◽  
Weighted Kernel ◽  
Global Regression ◽  
Data Points ◽  
Open Datasets

Geographically weighted regression (GWR) introduces the distance weighted kernel function to examine the non-stationarity of geographical phenomena and improve the performance of global regression. However, GWR calibration becomes critical when using a serial computing mode to process large volumes of data. To address this problem, an improved approach based on the compute unified device architecture (CUDA) parallel architecture fast-parallel-GWR (FPGWR) is proposed in this paper to efficiently handle the computational demands of performing GWR over millions of data points. FPGWR is capable of decomposing the serial process into parallel atomic modules and optimizing the memory usage. To verify the computing capability of FPGWR, we designed simulation datasets and performed corresponding testing experiments. We also compared the performance of FPGWR and other GWR software packages using open datasets. The results show that the runtime of FPGWR is negatively correlated with the CUDA core number, and the calculation efficiency of FPGWR achieves a rate of thousands or even tens of thousands times faster than the traditional GWR algorithms. FPGWR provides an effective tool for exploring spatial heterogeneity for large-scale geographic data (geodata).

Extending Biologically Integrated Farming Practices within the San Joaquin Valley's West Side

HortScience ◽  
1998 ◽  
Vol 33 (3) ◽  
pp. 530c-530
Author(s):  
J.P. Mitchell ◽  
P.B. Goodell ◽  
R.L. Coviello ◽  
T.S. Prather ◽  
D.M. May ◽  
...  
Keyword(s):  
Pest Management ◽  
Information Exchange ◽  
Large Scale ◽  
Management Practices ◽  
Organic Soil ◽  
The West ◽  
West Side ◽  
Row Crops ◽  
Research Activities ◽  
On Farm

The West Side On-Farm Demonstration Project is a large-scale extension program consisting of farmers, researchers, extension advisors from the Univ. of California, and other private and public agency consultants who are evaluating biologically integrated soil-building and pest management practices within a participatory and on-farm demonstration context. Modeled after the Biologically Integrated Orchard Systems (BIOS) Projects that were originally sponsored by the Community Alliance with Family Farmers, the goals of this project are to facilitate information exchange among West Side farmers, consultants and researchers on soil-building practices and options for reduced reliance on agrichemical inputs, to monitor and evaluate on-farm demonstrations of soil-building practices, including cover cropping and organic soil amendments, and to determine the extent to which IPM practices are utilized in row crops on the West Side and identify constraints preventing further adoption of biologially intensive pest management practices. The Project has generated several adjunct research activities and considerable regional attention. A summary of ongoing impact assessment efforts will be presented.

Sign in / Sign up

Export Citation Format

Share Document