Assessment of data fusion oriented on data mining approaches to enhance precision agriculture practices aimed at increase of Durum Wheat (Triticum turgidum L. var. durum) yield

Abstract

In 2050, world population will reach a total of 9 billion inhabitants and their food demand have to be satisfied. Durum wheat (Triticum turgidum L. var. durum) is one of the most important food crop and its consumption is increasing worldwide. Productivity growth in agriculture and profitable returns are strongly influenced by investment in research and development, where Precision Agriculture (PA) represents an innovative way to manage farms by introducing the Information and Communication Technology (ICT) into the production process. It is known that farms activities produce large amounts of data. Today ICT allows, with electronic and software systems, to collect and transfer automatically these data, thus increasing yields and profits. In this direction significant data are processed from agricultural production, and retrieved to extract useful information important to increase the knowledge base. Data from multiple data sources can be processed by a Data Fusion (DF) approach able to combine multiple data sources into an unique database system. Raw data are transformed into useful information, thus DF improves pattern recognition, analysis of growth factors, and relationship between crops and environments. Data Fusion is synonym of Data Integration, Sensor Fusion, and Image Fusion. By means of Data Mining (DM) it is possible to extract useful information from data of the production processes thus providing new outputs concerning product quality and product “health status”. The following literature take into account the DF and DM techniques applied to Precision Agriculture (PA) and to cultivation inputs (water, nitrogen, etc.) management. We report also last advances of DF and DM in modern agriculture and in precision durum wheat production.

Blockchain and Technologies Matching with the Case of Study of Vegetables Production

“…In this direction neural networks such as Long Short Term Memory (LSTM) [39] and Artificial Neural Networks (ANNs) [40] could also be applied for: • processing production inefficiencies: the LSTM/ANNs networks could predict sanitation inefficiencies by processing and crossing data of the experimental test of cultivation (in Fig. 7 is shown the experimental field used to acquire and to collect data for the preprocessing of vegetables); the BC will include data and information about sanitation test by adopting different no-chemical pre-treatment solutions; • delays in transport: the algorithms predict production according to metrological sales prediction [41], [42]; • risk of persistent contamination: the neural network could predict the contamination evolution by indicating the risk using different approaches for sanitation; • field condition prediction: precision agriculture and data mining [43], [44] could facilitate the data processing by analyzing other factors that could influence product sanitation such as hydric stress, temperature, humidity and evapotranspiration [45]. The production process traceability by BC could activate automatic smart contracts thus accelerating marketing and commercial processes.…”

Blockchain and Technologies Matching with the Case of Study of Vegetables Production

“…In this direction neural networks such as Long Short Term Memory (LSTM) [39] and Artificial Neural Networks (ANNs) [40] could also be applied for: • processing production inefficiencies: the LSTM/ANNs networks could predict sanitation inefficiencies by processing and crossing data of the experimental test of cultivation (in Fig. 7 is shown the experimental field used to acquire and to collect data for the preprocessing of vegetables); the BC will include data and information about sanitation test by adopting different no-chemical pre-treatment solutions; • delays in transport: the algorithms predict production according to metrological sales prediction [41], [42]; • risk of persistent contamination: the neural network could predict the contamination evolution by indicating the risk using different approaches for sanitation; • field condition prediction: precision agriculture and data mining [43], [44] could facilitate the data processing by analyzing other factors that could influence product sanitation such as hydric stress, temperature, humidity and evapotranspiration [45]. Fig.…”

A proposal for a multi‐domain data fusion strategy in a climate‐smart agriculture context

“…Approaches around data mining in agriculture have used different schemes to solve a variety of problems, from satellite images in the estimation of possible uses and land cover, to predicting production, yield, and incidence of diseases of a crop through machine learning techniques, among others (Mucherino et al., 2009; Patel and Patel, 2014; Milovic and Radojevic, 2015; Mistry and Shah, 2016; Kodeeshwari and Ilakkiya, 2017; D'Accolti et al., 2018; Ait Issad et al., 2019; Anton et al., 2019; Vignesh and Vinutha, 2020). In order to complement the previously mentioned approaches, Scopus, ScienceDirect, Google Scholar, IEEE Digital Library, and Springer Link databases were consulted.…”