Suivez les dernières actualités postées ici !

Coordinate reference systems

Table des matières GeoidEllipsoidsCartesian coordinatesGeodetic and geocentric coordinatesNon-projected and projected coordinatesWGS84 and Lambert 93 If there is one subject that is neglected when working with spatialized data, it is the reference coordinate system. In general, we try to spend as little time as possible on the subject – often because it’s not very clear – Read more about Coordinate reference systems[…]

How to generate spatially correlated data?

Table des matières Presentation of the method for generating cross-correlated spatial dataTheory of the methodLet’s first work on the proportion of noise for .Let us then work on the correlation between and Some little extras Generally speaking, when we want to evaluate the robustness and/or generality of an algorithm, we need to test it on Read more about How to generate spatially correlated data?[…]

Working with high-resolution data in precision agriculture

Table des matières Autocorrelation / Cross-correlationNoiseNoise and autocorrelationReliabily and data qualityA few words of conclusion 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, Read more about Working with high-resolution data in precision agriculture[…]

Producing profitability maps from yield maps?

Table des matières Yield and Profitability MapsHow do we value these profitability maps?What is the impact on value chain relationships?What are the limits to the use of profitability maps? In spite of the emulation around precision agriculture and digital agriculture in France, it is clear that these tools and solutions are not yet widespread in Read more about Producing profitability maps from yield maps?[…]

Filtering – Cleaning Yield Maps

Table des matières Why filter yield maps ?Typology of yield errorsSome additional elements 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 Read more about Filtering – Cleaning Yield Maps[…]

Yield maps in Precision Agriculture

Table des matières Yield monitors: one of the pioneer sources of PAAcquisition  of  within-field  yield  data:  combine  harvesters  and  yield monitorsCharacteristics of within-field dataProvision and usagesAdvantages and limits of within-field yield dataHow to valorize yield maps?One last criticism for manufacturers. This post should have been published a long time ago, especially since it was the Read more about Yield maps in Precision Agriculture[…]

Precision Agriculture in all intimacy

Table des matières Challenges of the agricultural sectorWhat is Precision Agriculture?How can Precision Agriculture play a role in the agro-ecological transition?The adoption of Precision Agriculture is a bit slow….Precision Agriculture: Between approval and contradictionData quality, still a major loser…To go further…Micro plot experiments VS On-farm experimentsNew skills to work in Precision Agriculture?Again and again the Read more about Precision Agriculture in all intimacy[…]

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

Table des matières Convolutional Neural NetworksImage DatabasesPackages and libraries to useKaggle Contest 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.), 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

Table des matières Initializing weights and biasesThe cross-entropy functionRegularization and Drop OutThe bias-variance dilemmaA little feedback on the hyper-parameters, with some new ones in the listSupervised, unsupervised and reinforcement learning 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 Read more about Neural network – Let’s try to demystify all this a little bit (2) – To go a little further[…]