Neural Modelling in the Exploration of the Biomethane Potential from Cattle Manure: A Case Study on Herds Structure from Wielkopolskie, Podlaskie, and Mazowieckie Voivodeships in Poland

Abstract

In the presented study, data on the size and structure of cattle herds in Wielkopolskie, Podlaskie, and Mazowieckie voivodeships in 2019 were analyzed and subjected to modelling with the use of artificial intelligence, namely artificial neural networks (ANNs). The potential amount of biogas (m3) from cattle manure and slurry for the analyzed provinces was as follows: for the Mazowieckie Voivodeship, 800,654,186 m3; for the Podlaskie voivodeship, 662,655,274 m3; and for the Wielkopolskie voivodeship, 657,571,373 m3. Neural modelling was applied to find the relationship between the structure of the herds and the amount of generated slurry and manure (biomethane potential), as well as to indicate the most important animal types participating in biogas production. In each of the analyzed cases, the three-layer MLP perceptron with a single hidden layer proved to be the most optimal network structure. Sensitivity analysis of the generated models concerning herd structure showed a significant contribution of dairy cows to the methanogenic potential for both slurry and manure. The amount of slurry produced in the Mazowieckie and Wielkopolskie voivodeships was influenced in turn by heifers (both 6–12 and 12–18 months old) and bulls 12–24 months old, and in the Podlaskie voivodeship by calves and heifers 6–12 months old. As for manure, in addition to cows, bulls 12–24 months old and heifers 12–18 represented the main factor for Mazowieckie and Wielkopolskie voivodeships, and heifers (both 6–12 and 12–18 months old) for Podlaskie voivodeship.

Neural Modelling in the Study of the Relationship between Herd Structure, Amount of Manure and Slurry Produced, and Location of Herds in Poland

“…Interestingly, none of the authors paid attention to the possible connection between biogas potential and the structure of the cattle herd. The presented work is a continuation of our earlier work on this issue [19]. We previously noticed that the animal keeping system resulting from the localisation might be of importance.…”

“…The obtained data included cattle counts for the selected provinces in Poland. -Conversion of voivodeship-level cattle numbers into livestock units (LSUs) using conversion factors provided by the 2010 GUS Agricultural Census [51] specifically designed for cattle and specific livestock systems (as described in our previous work [19]). -Calculation of the quantity of manure and slurry based on data from the GUS Agricultural Census 2010 [46].…”

“…In these areas, farmers are specialised in milk production. Farmers have implemented modern technologies of milk production, and cows' nutrition is mainly based on fodder from grassland [19]. Another important region of milk production, located in the centre of the country, includes Wielkopolskie, Kujawsko-Pomorskie, Łódzkie, and part of Opolskie voivodeship [20].…”

“…There are several scientific studies reported in the literature using machine learning or neural networks in agriculture and livestock production [26][27][28][29][30]. Usage of artificial intelligence in the form of artificial neural networks (ANNs) in modelling dairy cow herd parameters is relatively new, but promising [19,31]. ANNs are employed to forecast various production [23,32,33], health [34,35], and behaviour indicators [36] that are essential for managing dairy cow herds [37,38].…”

Factors Influencing Productivity and Sustainability of Small-Scale Beef Farms in Thailand

“…The results show that ANN generates predictions that are comparable to the logistic regression. Both models identified similar important factors influencing the intentions of farmers' descendants to continue careers in small-scale beef farms, i.e., the farm's reproductive management score, health management score and the respondent's occupation, suggesting that neural network analysis is an alternative method for ranking the remarkable factors related to personal attitudes as the neural network can learn from data and is able to handle noisy, complex and incomplete data in the livestock farm surveys (Wawrzyniak et al, 2022).…”