How to synthesize a history of vegetation maps on large parcels of land?

A short break from the classic files I write to return to my first love of spatialized data processing! This “small” dossier allows me to share and valorize the work done with a wine château during several vintages in a row. This chateau has the time and the means to collect high resolution data, but Read more about How to synthesize a history of vegetation maps on large parcels of land?[…]

More and more zoning : Classical zoning, Fuzzy Zoning, Constraint Zoning

In Precision Agriculture, the delimitation of within-field zones has become a fairly classic step in the processing chains of the services offered on the market (Figure 1). The creation of zones is mainly used to meet operational demands. These zones already simplify the reading of a Precision Agriculture map because it allows one to take Read more about More and more zoning : Classical zoning, Fuzzy Zoning, Constraint Zoning[…]

Codes R dans QGIS pour analyse spatiale

R codes to be used in QGIS and a QGIS plugin to work in Precision Agriculture

We propose, in Beta version, a set of R codes (more than forty) and a QGIS plugin to manipulate and process data acquired in the framework of Precision Agriculture. The R codes and the QGIS plugin can be retrieved from the Aspexit GitHub account. Remember to read the tutorials to learn how to retrieve the Read more about R codes to be used in QGIS and a QGIS plugin to work in Precision Agriculture[…]

Quantifying the within-field heterogeneity or variability in agriculture

There is no such thing as a perfectly homogenous agricultural field ! And this is simply due to the fact that we work with living organisms and that we are confronted with phenomena that are all more complex than each other (soil, climate, plants, agricultural practices…), and which also have the unfortunate tendency to interact Read more about Quantifying the within-field heterogeneity or variability in agriculture[…]

Linear modelling of spatial data in R

We will work here on a dataset that is fairly well known in spatial analysis – the “meuse” dataset – in order to reintroduce a number of concepts to those who would like to engage in linear modelling of spatialized data. This case study will be treated under the R language. One of the big Read more about Linear modelling of spatial data in R[…]

How to generate spatially correlated data?

Generally speaking, when we want to evaluate the robustness and/or generality of an algorithm, we need to test it on a large number of data, with quite varied characteristics, to ensure that the algorithm will give conclusive results in the vast majority of cases. If we had the means to have real data or field Read more about How to generate spatially correlated data?[…]

Working with high-resolution data in precision agriculture

Precision Agriculture is a data-based discipline; data that is collected to measure, describe, quantify, understand, or analyze agrosystems. A wide variety of measurement systems have been developed to measure agronomic parameters of interest, from plant vegetation status to crop yield, including weed detection and soil physico-chemical parameters. These increasingly sophisticated systems make it possible to Read more about Working with high-resolution data in precision agriculture[…]

Filtering – Cleaning Yield Maps

In the previous post, a fairly general picture of yield sensors and associated data was drawn. Here we return to a recurring question related to yield data: How can we ensure that yield data are reliable enough to be used properly? We will therefore review the main sources of uncertainty in these data sets; and Read more about Filtering – Cleaning Yield Maps[…]

Neural network – Let’s try to demystify all this a little bit (3) – Application to images

The complex architecture that we have detailed in detail in the previous sections is a multi-layer perceptron (MLP). This is the classic architecture of the neural network. Nevertheless, depending on the type of data used to input neural models (images, voice signal, etc.), more specific architectures have been implemented. To work with images, for example, Read more about Neural network – Let’s try to demystify all this a little bit (3) – Application to images[…]

Neural network – Let’s try to demystify all this a little bit (2) – To go a little further

With everything that has been presented in Part 1, I hope that you will have understood how a neural network works in general, with the two main steps of forward and back propagation. And that’s not bad enough, it’s a lot of concepts to mature! In this part, without going into too much detail either, Read more about Neural network – Let’s try to demystify all this a little bit (2) – To go a little further[…]