Niks Ozols

Mr. Niks Ozols

Plant protection and research institute Agrihorts, Latvia University of Life Sciences and Technologies, Jelgava, Jelgavas Novads, Latvia
orcid
Working

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 August 2020 in Data in Brief
Verified
Journal Article
Open access
KSKaspars Sudars
Kaspars Sudars
JJJanis Jasko
Janis Jasko
INIvars Namatevs
Ivars Namatevs
LOLiva Ozola
Liva Ozola
Niks OzolsNiks Ozols
Niks Ozols
Weed management technologies that can identify weeds and distinguish them from crops are in need of artificial intelligence solutions based on a computer vision approach, to enable the development of precisely targeted and autonomous robotic weed management systems. A prerequisite of such systems is to create robust and reliable object detection that can unambiguously distinguish weed from food crops. One of the essential steps towards precision agriculture is using annotated images to train convolutional neural networks to distinguish weed from food crops, which can be later followed using mechanical weed removal or selected spraying of herbicides. In this data paper, we propose an open-access dataset with manually annotated images for weed detection. The dataset is composed of 1118 images in which 6 food crops and 8 weed species are identified, altogether 7853 annotations were made in total. Three RGB digital cameras were used for image capturing: Intel RealSense D435, Canon EOS 800D, and Sony W800. The images were taken on food crops and weeds grown in controlled environment and field conditions at different growth stages.

27 April 2023 in PeerJ Computer Science
Verified
Journal Article
Open access
PDF file
AKArmands Kviesis
Armands Kviesis
VKVitalijs Komasilovs
Vitalijs Komasilovs
Niks OzolsNiks Ozols
Niks Ozols
AZAleksejs Zacepins
Aleksejs Zacepins
Information and communication technologies, specifically the Internet of Things (IoT), have been widely used in many agricultural practices, including beekeeping, where the adoption of advanced technologies has an increasing trend. Implementation of precision apiculture methods into beekeeping practice depends on availability and cost-effectiveness of honey bee colony monitoring systems. This study presents a developed bee colony monitoring system based on the IoT concept and using ESP8266 and ESP32 microchips. The monitoring system uses the ESP-NOW protocol for data exchange within the apiary and a GSM (Global System for Mobile communication)/GPRS (General packet radio service) external interface for packet-based communication with a remote server on the Internet. The local sensor network was constructed in a star type logical topology with one central node. The use of ESP-NOW protocol as a communication technology added an advantage of longer communication distance between measurement nodes in comparison to a previously used Wi-Fi based approach and faster data exchange. Within the study, five monitoring devices were used for real-time bee colony monitoring in Latvia. The bee colony monitoring took place from 01.06.2022 till 31.08.2022. Within this study, the distance between ESP-NOW enabled devices and power consumption of the monitoring and main nodes were evaluated as well. As a result, it was concluded that the ESP-NOW protocol is well suited for the IoT solution development for honeybee colony monitoring. It reduces the time needed to transmit data between nodes (over a large enough distance), therefore ensuring that the measurement nodes operate in an even lower power consumption mode.

1 August 2023 in Science of The Total Environment
Verified
Journal Article
Closed access
NLN. Leclercq
N. Leclercq
LML. Marshall
L. Marshall
TWT. Weekers
T. Weekers
PBP. Basu
P. Basu
DBD. Benda
D. Benda
NVN.J. Vereecken
N.J. Vereecken

28 November 2024 in Toxics
Verified
Journal Article
Open access
PDF file
Niks OzolsNiks Ozols
Niks Ozols
VBValters Brusbārdis
Valters Brusbārdis
MFMaksims Filipovičs
Maksims Filipovičs
JGJānis Gailis
Jānis Gailis
Vitalijs RadenkovsVitalijs Radenkovs
Vitalijs Radenkovs
VZViktorija Zagorska
Viktorija Zagorska
The honey bee (Apis mellifera) is the most widely managed pollinator and is vital for crop fertilization. Recently, bee colonies have been suffering high mortality rates, exacerbated by factors such as land-use changes and the use of pesticides. Our work aimed to explore the residues of pesticides in honey-bee-collected pollen and how this contamination was affected by seasonality and the landscape composition. We selected six apiaries from different landscapes in Latvia, and pollen samples were collected during the flowering season (2023). We analyzed 39 samples and found 21 pesticide residues (mainly fungicides) with a frequency of 93 occurrences where the values were above the limit of quantification. The most frequently encountered substances were acetamiprid, boscalid, fluopyram, and prothioconazole. However, the highest concentrations were for dimoxystrobin (44 µg kg−1), acetamiprid (37 µg kg−1), azoxystrobin (27 µg kg−1), prothioconazole (25 µg kg−1), and boscalid (15 µg kg−1). We then calculated the Pollen Hazard Quotient (PHQ) for each pollen sample. No sample had a PHQ value above the critical value of 50. The highest contamination level was observed in the first half of the vegetation season (the end of May and the beginning of June), but later, it significantly decreased. We did not find any significant influence of landscape composition on pesticide pollution.

1 December 2022 in Rural Sustainability Research
Verified
Journal Article
Open access
PDF file
Niks OzolsNiks Ozols
Niks Ozols
JGJānis Gailis
Jānis Gailis
IJInta Jakobija
Inta Jakobija
JJJānis Jaško
Jānis Jaško
VZViktorija Zagorska
Viktorija Zagorska
Bumblebee activity interaction with solar irradiation, solar irradiation and HPS lighting irradiation, the HPS effect of photoperiod, day temperature and hive density were assessed with tomato fruit weights in a commercial tomato glass greenhouse in 2020–2021. Pollination activity was measured by observing ten randomly chosen cv. ‘Beorange’ tomato plants and by counting bumblebee bruised tomato flowers. MANOVA was conducted between factors and bee activity, followed by Pearson’s correlation. A Mann-Whitney U test was calculated to determine the significance between tomato flower bruising levels and fruit weights, followed by Cliff’s delta (d). Pollination activity decreased mainly in December and January when solar irradiation decreased to below 110 J cm−2 day−1. Bumblebee activity was significantly affected by solar irradiation with HPS lighting (p<0.001; p<0.01). There was a significant correlation between bumblebee activity and solar irradiation (r= 0.75; p<0.05), and solar irradiation with HPS lighting (r= 0.70; p<0.05). There was no correlation between bumblebee activity and fruit weights (r= −0.20; p<0.05). Bruised flowers had significantly greater fruit weight increases (165.7 g) compared to unbruised flowers (123.4 g) (d= 0.12; p<0.05). Bee activity rates between 60% to 80% can be concluded as an effective rate for tomato growers. Bumblebees need at least 110–154 J cm−2 day−1 of solar irradiation to achieve a high pollination activity rate in temperate climate zones during the winter season.

1 August 2026 in Environmental Science and Pollution Research
Verified
Journal Article
Open access
PDF file
Niks OzolsNiks Ozols
Niks Ozols
MFMaksims Filipovičs
Maksims Filipovičs
BRBetija Rubene
Betija Rubene
SMSabīne Močāne
Sabīne Močāne
BTBaiba Tikuma
Baiba Tikuma
VZViktorija Zagorska
Viktorija Zagorska
Honey bees (Apis mellifera) are widely used as bioindicators of environmental contamination and bee-collected pollen reflects pesticide exposure in agricultural landscapes. This study evaluated pesticide residues in honey bee-collected pollen from six Latvian apiaries during 2024 and 2025 flowering seasons, and assessed toxicological risk using the Pollen Hazard Quotient (PHQ). In total, 15 active substances were detected in 2024 and 19 in 2025. Fungicides were the most frequently detected pesticide class in both years, accounting for 51% of detections in 2024 and 54% in 2025, followed by herbicides (38% and 24%) and insecticides (11% and 22%). The highest concentrations were recorded for glyphosate, fluazifop-P-butyl, boscalid, azoxystrobin, acetamiprid, and tebuconazole. Seasonal variation was evident, with higher residue concentrations and PHQ values mainly from mid-May to early July, coinciding with crop flowering and pesticide application periods. Median PHQ values remained below the threshold (PHQ < 50), however several samples in 2025 exceeded this level, with a maximum PHQ of 1173.91 driven by cypermethrin. No consistent descriptive pattern was observed between PHQ values and the proportion of agricultural land or nectar producing crops. This suggests that landscape composition alone did not explain differences in pesticide exposure among the studied apiaries. The results indicate that pesticide exposure is influenced by temporal variation, pesticide toxicity, and local factors such as crop management and foraging behaviour, rather than landscape composition alone. Honey bee-collected pollen proved to be a suitable tool for monitoring pesticide exposure. It also allowed the identification of periods of increased risk in agricultural environments.