Skoči na glavni sadržaj

Pregledni rad

https://doi.org/10.15255/KUI.2026.037

Digitalisation of Food Waste Valorisation: Application of Machine Learning Tools in Optimising the Composition of a Functional Food Product

Ana Jurinjak Tušek ; Sveučilište u Zagrebu Prehrambeno-biotehnološki fakultet, Pierrotijeva 6, 10 000 Zagreb *
Davor Valinger ; Sveučilište u Zagrebu Prehrambeno-biotehnološki fakultet, Pierrotijeva 6, 10 000 Zagreb
Tamara Jurina ; Sveučilište u Zagrebu Prehrambeno-biotehnološki fakultet, Pierrotijeva 6, 10 000 Zagreb
Maja Benković ; Sveučilište u Zagrebu Prehrambeno-biotehnološki fakultet, Pierrotijeva 6, 10 000 Zagreb
Jasenka Gajdoš Kljusurić ; Sveučilište u Zagrebu Prehrambeno-biotehnološki fakultet, Pierrotijeva 6, 10 000 Zagreb

* Dopisni autor.


Puni tekst: engleski pdf 1.426 Kb

str. 757-775

preuzimanja: 0

citiraj


Sažetak

Food waste represents a significant environmental, economic, and social challenge worldwide. The transition from conventional waste management practices toward circular bioeconomy concepts has encouraged the development of innovative food waste valorisation strategies aimed at recovering high-value compounds, functional ingredients, biofuels, and other value-added products. Recent advances in digital technologies have considerably enhanced the efficiency and sustainability of these processes. This review provides an overview of contemporary food waste valorisation approaches, including biological, chemical, and physical methods, and highlights the role of digital tools in improving process performance and product development. Particular emphasis is placed on the application of machine learning techniques in the optimisation of functional food products formulated from food waste-derived ingredients. Modern digital frameworks integrate data collected through advanced analytical methods, Internet of Things (IoT) systems, and sensor technologies, enabling real-time monitoring and data-driven decision-making. Machine learning models, such as artificial neural networks (ANNs), support vector machines (SVMs), random forests (RFs), and principal component analysis (PCA), facilitate prediction of product quality, optimisation of processing conditions, and identification of optimal ingredient formulations. Furthermore, software platforms including Python, MATLAB, Aspen Plus, and KNIME support modelling, simulation, visualisation, and optimisation of food waste valorisation processes. Despite the considerable potential of digitalisation, challenges related to data quality, technological infrastructure, model interpretability, economic feasibility, and regulatory compliance remain significant barriers to industrial implementation. Future developments are expected to focus on explainable artificial intelligence (XAI), digital twins, blockchain technologies, precision nutrition, and fully integrated smart biorefineries. The integration of digital technologies with food waste valorisation offers substantial opportunities for improving resource efficiency, reducing environmental impacts, and supporting the development of sustainable and innovative food systems.

Ključne riječi

food waste valorisation; machine learning; functional foods; digitalisation; circular bioeconomy

Hrčak ID:

353745

URI

https://hrcak.srce.hr/353745

Datum izdavanja:

21.11.2026.

Podaci na drugim jezicima: hrvatski

Posjeta: 0 *