EMU DSpace
Digitaalarhiiv EMU DSpace kogub, säilitab ja loob ligipääsu Eesti Maaülikooli liikmeskonna poolt loodud või Eesti Maaülikooli vastutusvaldkondadega seotud teadustöödele toetamaks maaülikooli konkurentsivõimet ja teadmistepõhist ühiskonna arengut. Digitaalarhiivi haldab Eesti Maaülikooli raamatukogu.
Valdkonnad DSpace's
Valige valdkond, et selle kogusid sirvida.
- Institute of Forestry and Engineering (MII)
- Institute of Agricultural and Environmental Sciences (PKI)
- Institute of Veterinary Medicine and Animal Sciences (VLI)
- Publications
- Units
Hiljutised sisestused
16th International Conference on Biosystems Engineering : May 6-8, 2026 in Tartu, Estonia : book of abstracts
(Estonian University of Life Sciences, 2026) Estonian University of Life Sciences; Olt, Jüri (editor); Kikas, Timo (editor); Meneses, Lisandra (editor)
Book of Abstracts. 16th International Conference on Biosystems Engineering 2026, May 6–8, 2025 Tartu, Estonia, Estonian University of Life Sciences.
Impact of the CEMOS AUTOMATIC intelligent system on the field performance and energy efficiency of a CLAAS LEXION 770 combine harvester
(Estonian University of Life Sciences, 2026) Hristova, G.; Veleva, P.; Patev, T.
Efficient management of combine harvesters is a key factor in modern precision agriculture, where automation and intelligent control systems play an essential role in optimizing operational performance and energy efficiency. This study presents a comparative analysis of the CLAAS LEXION 770 combine harvester operating with and without the CEMOS AUTOMATIC intelligent optimization system during wheat harvesting (Avenue variety). Field experiments were conducted to evaluate key performance indicators, including grain losses, fuel consumption, engine load, and throughput capacity under real harvesting conditions. The results show that the use of the CEMOS AUTOMATIC system improved fuel efficiency by 7–10%, reduced grain losses by 15–20%, and provided more stable machine operation compared with manual control. Furthermore, the intelligent control algorithm optimized the settings of threshing and cleaning systems in real time, resulting in improved productivity and reduced operator workload. The findings confirm that the integration of automated optimization systems such as CEMOS AUTOMATIC significantly enhances the energy efficiency and sustainability of modern harvesting operations.
An Explainable AI-Driven Framework for Precision Agriculture: A Comprehensive Survey
(Estonian University of Life Sciences, 2026) Dhotre, A.D.; Thorat, S.A.; Yelure, B.S.; Jawade, P.B.
This review focuses on crop recommendation systems and provides a thorough explanation of Explainable AI (XAI) in precision agriculture. The paper charts the development of predictive models that have been published in the literature, from straightforward, comprehensible algorithms to extremely accurate ‘black box’ ensemble and deep learning models, as well as their lack of transparency, which may erode farmers' confidence. In order to make these black box algorithms comprehensible and useful, the paper focuses on two XAI frameworks – LIME and SHAP – that are currently in use. The accuracy and explainability trade-off, problems with data heterogeneity, and the requirement for relevant user explanations are just a few of the significant gaps in the evidence base that are highlighted by the paper's synthesis of the research. The paper's concluding remarks provide a potential path toward integrated, reliable, and comprehensible AI systems that will enhance contemporary sustainable agriculture.
Potentially fatal incidents: identification, classification and human factor analysis
(Estonian University of Life Sciences, 2026) Lezdkalne, J.
Potentially fatal incidents (PFIs) are increasingly used as leading indicators in high-risk industries, yet their definitions, classification criteria, and investigative depth vary widely across organisations, limiting. their preventive value and comparability. Human factors (HF) play a critical role in determining whether incidents escalate into PFIs and must be considered together with technical and organisational barrier performance. This research aims to examine the role of human and organisational factors in PFI identification, analyse misclassification patterns, and propose a human-factors-based model to improve PFI classification consistency and learning value. A retrospective document analysis was conducted using incident reports from a heavy-industry organisation covering the period from 2020 to 2024. The dataset was systematically reviewed and PFI classifications were re-evaluated using a structured framework integrating hazardous energy and exposure assessment, barrier performance evaluation based on Bow-Tie logic, and human and organisational factor coding using an HFACS-based structure. Analysis revealed inconsistency in PFI classification, including overclassification and under-classification linked to limited recognition of human and organisational factors. Number of incidents were labelled as PFIs despite lacking credible fatal energy exposure, while other events with systemic and human-factor contributors associated with fatal risk were not recognised as PFIs. The HF-PFI Model demonstrated improved classification reliability by integrating energy exposure, barrier status, human factor categories, and systemic indicators. Integrating human-factors analysis into PFI identification can strengthen serious injury and fatality prevention in high-risk industrial environments.
Influence of anthropogenic factors on humus in Phaeozems of Ashotsk land cadastral district
(Estonian University of Life Sciences, 2026) Kroyan, S.Z.; Baghdasaryan, S.K.; Markosyan, S.A.; Kroyan, N.S.; Zadayan, M.H.; Markosyan, A.O.
The study was conducted on Phaeozems of the Ashotsk land cadastral region (ALCR), Republic of Armenia. Field investigations compared virgin and long-term cultivated soil variants. Total humus content was determined using the Tyurin method, and the qualitative composition of humus was analyzed according to the Kononova and Belchikova procedure. The results demonstrated that in the plough horizon of cultivated soils, the content and total stock of humic acids, fulvic acids, and non-hydrolyzable residue decreased by 18%, 15.6%, and 17%, respectively. Under prolonged agricultural use, both quantitative and qualitative humus characteristics changed considerably. Compared with virgin soils, total humus content declined by approximately 32%, while humic and fulvic acid fractions decreased by 16–18%. These findings confirm progressive deterioration of humus in cultivated Phaeozems and highlight the necessity of fertility restoration measures. Management practices that may be considered include the application of organic fertilizers (55–65 t ha-1) combined with mineral fertilizers in prescribed doses (N90, P100, K60) and the implementation of minimum or zero tillage within adaptive landscape farming systems.