Data Fusion and Artificial Neural Networks for Modelling Crop Disease Severity

Abstract

This paper analyzes the possibility of applying data fusion combined with artificial neural networks (ANN) on a dataset combining hard and soft data for prediction of one of the most devastating crop diseases of winter wheat, i.e., Septoria Tritici (Zymoseptoria tritici). In advanced decision support systems for crop protection choices, disease models form a major component. They reproduce the biophysical processes of disease development and temporal spread as a set of rules or processes to predict disease risk value. However, the adaptation of these rules or processes to incorporate the effects of climate change is complex and requires extensive rework. To remedy this issue, statistical machine learning techniques have been introduced to model disease severity percentage for some diseases. However, the use of artificial neural networks has been limited (mainly to image data) and is unexplored for Septoria Tritici. This paper explores the use of Feed Forward neural networks on fused tabular data for the task of disease severity modelling. First, ten years of trial data ranging from 2008 to 2018 across Europe is used for the creation of the new tabular dataset with a fusion of all important data sources baring impact on disease development: Field-specific data, weather data, crop growth stages, and disease severity observation made by human trial operators (response variable). Next, two implementation architectures of Feed Forward neural networks on tabular data are employed: a) standard architecture with backpropagation, drop out regularization, and batch normalization and b) advanced architecture with improvements such as cyclic learning rate and cosine annealing. The advanced architecture is able to better model the data and make estimations of disease severity with a difference of +-10% giving a better quantifiable estimate of disease stress. For better outreach to farmers, a technique to incorporate such modelling techniques into the well established Decision Support Systems is also presented.

Data Fusion in Agriculture: Resolving Ambiguities and Closing Data Gaps

“…Some of the studies considered in this article use types of data that are more particular and do not fit a general category, normally in combination with some of the more commonly used variables [ 24 , 44 , 64 , 67 , 93 ]. In general, the performance of the data fusion reported on in those cases compares favorably with single data sources, although some difficulties related with data compatibility have also been reported [ 82 , 129 ].…”

“…Machine learning techniques have been applied to a wide variety of problems since (at least) the 1990s. In the case of data fusion in agriculture, techniques, such as fuzzy logic [ 18 ], random forest [ 78 , 82 ], support vector machines [ 83 , 92 , 113 ], k-nearest neighbors [ 90 ], and shallow neural networks [ 24 , 69 , 85 ] have been employed, often showing advantages when digital images were involved, but without ever dominating other strategies. This began to change with the inception of deep neural networks.…”

“…In the specific case of agriculture, data can be collected at three different scales—proximal, aerial, and orbital (satellites) ( Figure 1 ). Applications that use proximal data include navigation systems for autonomous vehicles [ 11 , 12 , 13 , 14 , 15 , 16 , 17 ], fruit detection [ 18 , 19 , 20 , 21 ], plant disease detection [ 22 , 23 , 24 ], delineation of homogeneous management zones [ 25 , 26 , 27 , 28 , 29 ], soil analysis [ 30 , 31 , 32 , 33 , 34 , 35 , 36 ], plant phenotyping [ 37 ], among others. Aerial data (collected using UAVs) is used mostly for detection of certain objects (e.g., certain plant species and fruits) [ 38 ] and for estimation of agricultural variables (e.g., soil moisture and nitrogen content) [ 39 , 40 , 41 ].…”

Boosting precision crop protection towards agriculture 5.0 via machine learning and emerging technologies: A contextual review

“…climate data, proximal and remote sensing, crop and soil sensors, farm management information systems, etc.) and assess the spatio-temporal occurrence and severity of the pests ( Shankar et al., 2020 ), which will lead to improve early detectors and diagnostic algorithms ( Picon et al., 2019 ; Ramcharan et al., 2019 ). On the other side, the latter aims the design of powerful autonomous systems capable of simultaneously doing the three main stages of precision crop protection in real time (see section 2), i.e.…”