G. Milics

16316996800

Publications - 16

Yield Prediction Using NDVI Values from GreenSeeker and MicaSense Cameras at Different Stages of Winter Wheat Phenology

G. Milics Viktoria Vona Gabor Kukorelli Zoltán Varga A. J. Kovács István Mihály Kulmány Laszló Bede Gergely Teschner Sándor Zsebő Dávid Stencinger

Publication Name: Drones

Publication Date: 2024-03-01

Volume: 8

Issue: 3

Page Range: Unknown

Description:

This work aims to compare and statistically analyze Normalized Difference Vegetation Index (NDVI) values provided by GreenSeeker handheld crop sensor measurements and calculate NDVI values derived from the MicaSense RedEdge-MX Dual Camera, to predict in-season winter wheat (Triticum aestivum L.) yield, improving a yield prediction model with cumulative growing degree days (CGDD) and days from sowing (DFS) data. The study area was located in Mosonmagyaróvár, Hungary. A small-scale field trial in winter wheat was constructed as a randomized block design including Environmental: N-135.3, P2O5-77.5, K2O-0; Balance: N-135.1, P2O5-91, K2O-0; Genezis: N-135, P2O5-75, K2O-45; and Control: N, P, K 0 kg/ha. The crop growth was monitored every second week between April and June 2022 and 2023, respectively. NDVI measurements recorded by GreenSeeker were taken at three pre-defined GPS points for each plot; NDVI values based on the MicaSense camera Red and NIR bands were calculated for the same points. Results showed a significant difference (p ≤ 0.05) between the Control and treated areas by GreenSeeker measurements and Micasense-based calculated NDVI values throughout the growing season, except for the heading stage. At the heading stage, significant differences could be measured by GreenSeeker. However, remotely sensed images did not show significant differences between the treated and Control parcels. Nevertheless, both sensors were found suitable for yield prediction, and 226 DAS was the most appropriate date for predicting winter wheat’s yield in treated plots based on NDVI values and meteorological data.

Open Access: Yes

DOI: 10.3390/drones8030088

Impact of environmental conditions on the distribution of insect pests in Nitra region vineyards (Slovakia)

G. Milics Pavel Beracko Igor Matečný Rita Abrahám Veronika Beranová

Publication Name: Geographia Cassoviensis

Publication Date: 2022-12-30

Volume: 16

Issue: 2

Page Range: 130-146

Description:

The presented study introduces the most common and significant insect pests of the grapevine (Vitis xinifera) in Slovakia, specifically the occurrence of the European grapevine moth (Lobesia botrana) and the American grapevine leafhopper (Scaphoideus titanus). Historical records set prerequisites to studying the complex interactions between the pests and their host plant. If they are not understood sufficiently, they may have devastating consequences on the grape-growing. The research was carried out in the model vineyards in Jelenec, Ladice and Topol'čianky during the period from April to September 2019 and 2021. Jelenec and Ladice had six monitoring sites, Topol'čianky had seven monitoring sites. Data were collected in approximately 30-day cycles. The aim of research was to monitor the incidence of insect pests in selected vineyards and identify' their relation to environmental conditions. Pheromone traps were used throughout the research. The insect traps in combination with species-specific pheromone represent a reliable method for the pest monitoring. Based on aim studying the link between insect pests and climate conditions, traps were dispersed at the place of installation of the microclimatic dataloggers and the automatic stations. Data on the occurrence of the pests were subsequently evaluated in the context of the climate variability (temperature, wind speed, precipitation) and distance of the locality from the forest using Redundancy Analysis. It was confirmed that the insect pests are unequally distributed in the studied region and also inside the vineyards. Using Redundancy Analysis, we were able to explain the bonds in a maximum of 40% insect pests-environmental factors relationships. This research results show the need for regular monitoring of insect species, taking into account microclimatic as well as other ecological factors to optimize agrotechnical interventions.

Open Access: Yes

DOI: 10.33542/GC2022-2-04

The effect of local samples in the accuracy of mid-infrared (MIR) and X-ray fluorescence (XRF) -based spectral prediction models

Csaba Centeri Renato Kalocsai G. Milics Márton Vona Viktoria Vona B. Tomczyk A. Vér István Mihály Kulmány S. Sarjant Gergely Jakab

Publication Name: Precision Agriculture

Publication Date: 2022-12-01

Volume: 23

Issue: 6

Page Range: 2027-2039

Description:

Within the soil spectroscopy community, there is an ongoing discussion addressing the comparison of the performance of prediction models built on a global calibration database, versus a local calibration database. In this study, this issue is addressed by spiking of global databases with local samples. The soil samples were analysed with MIR and XRF sensors. The samples were further measured using traditional wet chemistry methods to build the prediction models for seventeen major parameters. The prediction models applied by AgroCares, the company that assisted in this study, combine spectral information from MIR and XRF into a single ‘fused-spectrum’. The local dataset of 640 samples was split into 90% train and 10% test samples. To illustrate the benefits of using local calibration samples, three separate prediction models were built per element. For each model, 0%, 50% (randomly selected) and 100% of the local training samples were added to the global dataset. The remaining 10% local samples were used for validation. Seventeen soil parameters were selected to illustrate the differences in performance across a range of soil qualities, using the validation set to measure performance. The results showed that many models already exhibit an excellent level of performance (R2 ≥ 0.95) even without local samples. However, there was a clear trend that, as more local calibration samples were added, both R2 and ratio of performance to interquantile distance (RPIQ) increase.

Open Access: Yes

DOI: 10.1007/s11119-022-09942-y

Calibration of an Arduino-based low-cost capacitive soil moisture sensor for smart agriculture

G. Milics Viktoria Vona Ákos Bede-Fazekas Márk Kovács István Mihály Kulmány Laszló Bede Ana Beslin Bálint Ambrus Barna Kovács Zsolt Giczi

Publication Name: Journal of Hydrology and Hydromechanics

Publication Date: 2022-09-01

Volume: 70

Issue: 3

Page Range: 330-340

Description:

Agriculture faces several challenges to use the available resources in a more environmentally sustainable manner. One of the most significant is to develop sustainable water management. The modern Internet of Things (IoT) techniques with real-time data collection and visualisation can play an important role in monitoring the readily available moisture in the soil. An automated Arduino-based low-cost capacitive soil moisture sensor has been calibrated and developed for data acquisition. A sensor- and soil-specific calibration was performed for the soil moisture sensors (SKU:SEN0193 - DFROBOT, Shanghai, China). A Repeatability and Reproducibility study was conducted by range of mean methods on clay loam, sandy loam and silt loam soil textures. The calibration process was based on the data provided by the capacitive sensors and the continuously and parallelly measured soil moisture content by the thermogravimetric method. It can be stated that the response of the sensors to changes in soil moisture differs from each other, which was also greatly influenced by different soil textures. Therefore, the calibration according to soil texture was required to ensure adequate measurement accuracy. After the calibration, it was found that a polynomial calibration function (R2 ≥ 0.89) was the most appropriate way for modelling the behaviour of the sensors at different soil textures.

Open Access: Yes

DOI: 10.2478/johh-2022-0014

Lessons to be learned in adoption of autonomous equipment for field crops

Tyler Mark Karl Behrendt G. Milics James Lowenberg-DeBoer Jordan Shockley Melf Hinrich Ehlers David Rose Iona Yuelu Huang Kehinde Oluseyi Olagunju Søren Marcus Pedersen Ian Kumwenda Carl Dillon Andreas Gabriel Andreas Meyer-Aurich

Publication Name: Applied Economic Perspectives and Policy

Publication Date: 2022-06-01

Volume: 44

Issue: 2

Page Range: 848-864

Description:

Autonomous equipment for crop production is on the verge of technical and economic feasibility, but government regulation may slow its adoption. Key regulatory issues include requirements for on-site human supervision, liability for autonomous machine error, and intellectual property in robotic learning. As an example of the impact of regulation on the economic benefits of autonomous crop equipment, analysis from the United Kingdom suggests that requiring 100% on-site human supervision almost wipes out the economic benefits of autonomous crop equipment for small and medium farms and increases the economies-of-scale advantage of larger farms.

Open Access: Yes

DOI: 10.1002/aepp.13177

Comparing Different Phosphorus Extraction Methods: Effects of Influencing Parameters

Csaba Centeri Renato Kalocsai G. Milics Márton Vona Zsolt Biró Viktoria Vona A. J. Kovács J. Kauser István Mihály Kulmány Gergely Jakab

Publication Name: Sustainability Switzerland

Publication Date: 2022-02-01

Volume: 14

Issue: 4

Page Range: Unknown

Description:

The current study compares the phosphorus (P) analysis methods of ammonium lactate (AL), Mehlich 3 (M3); water extraction (P-WA(P)&P-WA(PO4 )), cobalt hexamine (CoHex) and X-ray fluorescence (XRF) as an estimate of total soil P. The ratio of the P-content/XRF was first calculated and compared with the whole dataset. Based on the comparison of all the data, there were significant differences between the results of P-WA(P) and P-WA(PO4 ) vs. M3 and AL, CoHex vs. M3 and CoHex vs. AL methods (p < 0.001). The second step was the analysis of the influencing factors based on their categories for a more in-depth understanding of their role (CaCO3-content, pH, soil texture and clay content). The results showed that higher CaCO3 content (>1%) resulted in lower correlations (6/10 cases). The extraction methods, the soil, the classification method of the soil properties and the statistical analyses affect the evaluation. The dataset covers a good range of the analysed factors for the evaluation of phosphorus in the majority of Hungarian soil types in arable use. There were two methods that detected the largest amount of P from the total P in the soil: AL and M3.

Open Access: Yes

DOI: 10.3390/su14042158

Conference report from 13th European Conference on Precision Agriculture (ECPA)

G. Milics A. J. Kovács A. Nyéki M. Neményi

Publication Name: Environmental Sciences Europe

Publication Date: 2021-12-01

Volume: 33

Issue: 1

Page Range: Unknown

Description:

This is a report on the 13th European Conference on Precision Agriculture (ECPA) that took place between 18 and 22, July at the location of the University of Public Service in Budapest, Hungary. The theme of the Conference was the “Adoption of innovative precision agriculture technologies and solutions”. Due to the pandemic, the conference was a hybrid event. The two societies—the International Society of Precision Agriculture and the Hungarian Society of Precision Agriculture—had contributed to the event. The international conference was mainly attended by academic researchers, university instructors, company executives and farmers. The event comprised five plenary and 22 scientific sessions.

Open Access: Yes

DOI: 10.1186/s12302-021-00559-y

Application of spatio-temporal data in site-specific maize yield prediction with machine learning methods

E. Harsányi G. Milics Bálint Daróczy C. Kerepesi A. J. Kovács J. Nagy A. Nyéki M. Neményi András Benczúr

Publication Name: Precision Agriculture

Publication Date: 2021-10-01

Volume: 22

Issue: 5

Page Range: 1397-1415

Description:

In order to meet the requirements of sustainability and to determine yield drivers and limiting factors, it is now more likely that traditional yield modelling will be carried out using artificial intelligence (AI). The aim of this study was to predict maize yields using AI that uses spatio-temporal training data. The paper has advanced a new method of maize yield prediction, which is based on spatio-temporal data mining. To find the best solution, various models were used: counter-propagation artificial neural networks (CP-ANNs), XY-fused Querynetworks (XY-Fs), supervised Kohonen networks (SKNs), neural networks with Rectangular Linear Activations (ReLU), extreme gradient boosting (XGBoost), support-vector machine (SVM), and different subsets of the independent variables in five vegetation periods. Input variables for modelling included: soil parameters (pH, P2O5, K2O, Zn, clay content, ECa, draught force, Cone index), micro-relief averages, and meteorological parameters for the 63 treatment units in a 15.3 ha research field. The best performing method (XGBoost) reached 92.1% and 95.3% accuracy on the training and the test sets. Additionally, a novel method was introduced to treat individual units in a lattice system. The lattice-based smoothing performed an additional increase in Area under the curve (AUC) to 97.5% over the individual predictions of the XGBoost model. The models were developed using 48 different subsets of variables to determine which variables consistently contributed to prediction accuracy. By comparing the resulting models, it was shown that the best regression model was Extreme Gradient Boosting Trees, with 92.1% accuracy (on the training set). In addition, the method calculates the influence of the spatial distribution of site-specific soil fertility on maize grain yields. This paper provides a new method of spatio-temporal data analyses, taking the most important influencing factors on maize yields into account.

Open Access: Yes

DOI: 10.1007/s11119-021-09833-8

A coupled impact of different management and soil moisture on yield of winter wheat (Triticum aestivum L.) in dry conditions at locality Mezoföld, Hungary

G. Milics

Publication Name: Journal of Hydrology and Hydromechanics

Publication Date: 2021-03-01

Volume: 69

Issue: 1

Page Range: 76-86

Description:

Variable rate technology (VRT) in nutrient management has been developed in order to apply crop inputs according to the required amount of fertilizers. Meteorological conditions rarely differ within one field; however, differences in soil conditions responding to precipitation or evaporation results within field variations. These variations in soil properties such as moisture content, evapotranspiration ability, etc. requires site-specific treatments for the produced crops. There is an ongoing debate among experts on how to define management zones as well as how to define the required amount of fertilizers for phosphorus and nitrogen replenishment for winter wheat (Triticum aestivum L.) production. For management zone delineation, vegetation based or soil based data collection is applied, where various sensor technology or remote sensing is in help for the farmers. The objective of the study reported in this paper was to investigate the effect of soil moisture data derived from Sentinel-2 satellite images moisture index and variable rate phosphorus and nitrogen fertilizer by means of variable rate application (VRA) in winter wheat in Mezoföld, Hungary. Satellite based moisture index variance at the time of sowing has been derived, calculated and later used for data comparison. Data for selected points showed strong correlation (R2 = 0.8056; n = 6) between moisture index and yield, however generally for the whole field correlation does not appear. Vegetation monitoring has been carried out by means of NDVI data calculation. On the field level, as indicated earlier neither moisture index values at sowing nor vegetation index data was sufficient to determine yield. Winter wheat production based on VRA treatment resulted significant increase in harvested crop: 5.07 t/h in 2013 compared to 8.9 t/ha in 2018. Uniformly managed (control) areas provided similar yield as VRA treated areas (8.82 and 8.9 t/ha, respectively); however, the input fertilizer was reduced by 108 kg/ha N and increased by 37 kg/ha P.

Open Access: Yes

DOI: 10.2478/johh-2020-0039

The effect of soil physicochemical characteristics on zinc analysis methods

Csaba Centeri Renato Kalocsai G. Milics Zsolt Biró Viktoria Vona A. J. Kovács Endre Andor Tóth István Mihály Kulmány Gergely Jakab Zsolt Giczi

Publication Name: Soil and Water Research

Publication Date: 2021-01-01

Volume: 16

Issue: 3

Page Range: 180-190

Description:

Zn is an essential micronutrient involved in a wide variety of physiological processes. Soils are tested for zinc in many countries with several extractants. Each country has its validated methods, best-suited for its soils. The current study was designed to compare different zinc content measuring methods with seventy-one samples from Hungary. The data were first compared for the whole dataset and then in certain categories such as CaCO3-content, pH, texture and clay content. The zinc content was determined by the water extraction, KCl-EDTA (ethylenediaminetetraacetic acid), Mehlich 3, CoHex (cobalt hexamine trichloride), and XRF (X-ray fluorescence) methods. Based on the analyses of all the data, we can conclude that all the methods are different. However, further analyses during the comparison of the methods based on the influencing factors, such as the pH, lime content, texture class, and clay content proved that, in some of the cases, there are similarities among the methods and, this way, we can get more knowledge on the measurements and the results provided. Farmers can gain extra knowledge from the comparison of the influencing factors to know where intervention is needed to use extra Zn for the proper fertilisation of their plants.

Open Access: Yes

DOI: 10.17221/53/2020-SWR

Comparison of magnesium determination methods on Hungarian soils

Csaba Centeri Renato Kalocsai G. Milics Zsolt Biró Viktoria Vona A. J. Kovács Gergely Jakab Zsolt Giczi

Publication Name: Soil and Water Research

Publication Date: 2020-01-01

Volume: 15

Issue: 3

Page Range: 173-180

Description:

Magnesium is one of the most important nutrient elements. Soils are tested for magnesium in many countries with several extractants. Each country has its own validated methods, best-suited for its soils. The current study was designed to compare different magnesium content measuring methods with 80 Hungarian samples. The magnesium content was determined by the potassium chloride (1 M KCl 1:10), Mehlich 3 and CoHex (cobalt hexamine trichloride) methods. The maximum, mean and median values resulting from all the Mg determination methods showed the following order of measured magnitude: KCl < CoHex < M3.

Open Access: Yes

DOI: 10.17221/92/2019-SWR

Drivers of Ambrosia artemisiifolia abundance in arable fields along the Austrian-Hungarian border

G. Milics B. Czúcz Ákos Bede-Fazekas Gy Pinke K. Nagy A. Vér Tamás Kolejanisz Gerhard Schlögl Z. Botta-Dukát

Publication Name: Preslia

Publication Date: 2019-12-06

Volume: 91

Issue: 4

Page Range: 369-389

Description:

The Carpathian Basin is one of the most important regions in terms of the invasion of the common ragweed (Ambrosia artemisiifolia) in Europe. The invasion history of this weed, however, seems to have been assessed differently in Austria and Hungary: Scientists in both countries assumed that this species had become abundant earlier and had caused more problems in their own than in other country. The goal of this study is to resolve the historical misunderstandings and scrutinize the related popular beliefs by a concise literature overview and an extensive analysis of the current patterns in ragweed infestations in crops in the borderlands in eastern Austria and western Hungary. The abundance of A. artemisiifolia was measured in 200 arable fields across the region, along with 31 background variables. Data were analysed using binomial generalized linear models (GLM), decision tree models and variation partitioning. Ambrosia artemisiifolia occurred more frequently in Hungary, but there were no significant differences in the proportion of larger cover values recorded in these two countries, and 'cover values > 10%' were even slightly more common in Austria.We found that previous crops of maize and soya bean and conventional farming were associated with the higher abundances in Austria, while organic farming was associated with relatively higher frequencies of heavy infestations in Hungarian fields. In the overall analysis crop cover was the most important variable with low crop cover associated with high ragweed abundance. Temperature and phosphorous fertilizer were negatively, while precipitation and soil phosphorous concentration positively associated with the abundance values. Land-use variables accounted for more of the variance in the abundance patterns of common ragweed than environmental variables. The current patterns in ragweed distributionmight indicate that a saturation process is still underway on the Austrian side. The saturation lag of 20-30 years is possibly due to several factors and the role of the Iron Curtain in determining cross-border exchange of propagules could be decisive. Nevertheless, the discrepancies uncovered in the accounts of the invasion of Hungarian and Austrian authors might also be seen as legacies of the Iron Curtain, which were caused by mutual limitations on access to national data and literature of the other country in a critical period of rapid ragweed spread. These discrepancies, that had a long-lasting effect on the work of scientific communities, are documented here in detail for the first time.

Open Access: Yes

DOI: 10.23855/PRESLIA.2019.369

Maize yield prediction based on artificial intelligence using spatio-temporal data

G. Milics Bálint Daróczy C. Kerepesi A. J. Kovács A. Nyéki M. Neményi András Benczúr

Publication Name: Precision Agriculture 2019 Papers Presented at the 12th European Conference on Precision Agriculture Ecpa 2019

Publication Date: 2019-01-01

Volume: Unknown

Issue: Unknown

Page Range: 1011-1017

Description:

The aim of this study was to predict maize yield by artificial intelligence using spatio-temporal training data. Counter-propagation artificial neural networks (CP-ANNs), XY-fused networks (XY-Fs), supervised Kohonen networks (SKNs), extreme gradient boosting (XGBoost) and support-vector machine (SVM) were used for predicting maize yield in 5 vegetation periods. Input variables for modelling were: soil parameters (pH, P2O5, K2O, Zn, Clay content, ECa, draught force, Cone index), and micro-relief averages and meteorological parameters for the 63 treatment units. The best performing method (XGBoost) attained 92.1 and 95.3% of accuracy on the training and the test set.

Open Access: Yes

DOI: 10.3920/978-90-8686-888-9_124

Effect of variable rate phosphorus and nitrogen fertilizing on winter wheat (Triticum aestivum L.) in Mezőföld, Hungary

G. Milics A. Vér L. Szekeres J. Kauser

Publication Name: Precision Agriculture 2019 Papers Presented at the 12th European Conference on Precision Agriculture Ecpa 2019

Publication Date: 2019-01-01

Volume: Unknown

Issue: Unknown

Page Range: 547-553

Description:

Variable rate technology (VRT) in nutrient management has been developed in order to apply crop inputs according to the required amount of fertilizers. There is an ongoing debate among experts on how to define management zones as well as how to define the required amount of fertilizers for phosphorus and nitrogen replenishment for winter wheat (Triticum aestivum L.) production. The objective of the study reported in this paper was to investigate the effect of variable rate phosphorus and nitrogen fertilizer application in winter wheat in Mezőföld, Hungary. Winter wheat production based on variable rate nutrient treatment resulted in 1.19 t/ha more yield than the farm average while applying an average 108 kg/ha less nitrogen and 37 kg/ha more phosphorus fertilizer.

Open Access: Yes

DOI: 10.3920/978-90-8686-888-9_68

Soil moisture distribution mapping in topsoil and its effect on maize yield

Viliam Nagy G. Milics Zoltán Varga A. J. Kovács Attila Pörneczi Gábor Baranyai A. Nyéki Lubomír Lichner M. Neményi Tamás Németh

Publication Name: Biologia Poland

Publication Date: 2017-08-28

Volume: 72

Issue: 8

Page Range: 847-853

Description:

Soil moisture content directly influences yield. Mapping within field soil moisture content differences provides information for agricultural management practices. In this study we aimed to find a cost-effective method for mapping within field soil moisture content differences. Spatial coverage of the field sampling or TDR method is still not dense enough for site-specific soil management. Soil moisture content can be calculated by measuring the apparent soil electrical conductivity (ECa) using the Veris Soil EC-3100 on-the-go soil mapping tool. ECa is temperature dependent; therefore values collected in different circumstances were standardized to 25°C temperature (EC25). Constants for Archie's adjusted law were calculated separately, using soil temperature data. According to our results, volumetric moisture content can be mapped by applying ECa measurements in our particular field with high spatial accuracy. Even though within-field differences occure in the raw ECa map standardization to EC25 is recommended. Soil moisture map was also compared to yield map showing correlation (R2 = 0.5947) between the two datasets.

Open Access: Yes

DOI: 10.1515/biolog-2017-0100

Effects of soil compaction on cereal yield: A review

G. Milics A. J. Kovács A. Nyéki M. Neményi

Publication Name: Cereal Research Communications

Publication Date: 2017-03-01

Volume: 45

Issue: 1

Page Range: 1-22

Description:

This paper reviews the works related to the effect of soil compaction on cereal yield and focuses on research of field experiments. The reasons for compaction formation are usually a combination of several types of interactions. Therefore one of the most researched topics all over the world is the changes in the soil's physical and chemical properties to achieve sustainable cereal production conditions. Whether we are talking about soil bulk density, physical soil properties, water conductivity or electrical conductivity, or based on the results of measurements of on-line or point of soil sampling resistance testing, the fact is more and more information is at our disposal to find answers to the challenges. Thanks to precision plant production technologies (PA) these challenges can be overcome in a much more efficient way than earlier as instruments are available (geospatial technologies such as GIS, remote sensing, GPS with integrated sensors and steering systems; plant physiological models, such Decision Support System for Agrotechnology Transfer (DSSAT), which includes models for cereals etc.). The tests were carried out first of all on alteration clay and sand content in loam, sandy loam and silt loam soils. In the study we examined especially the change in natural soil compaction conditions and its effect on cereal yields. Both the literature and our own investigations have shown that the soil moisture content changes have the opposite effect in natural compaction in clay and sand content related to cereal yield. These skills would contribute to the spreading of environmental, sustainable fertilizing devoid of nitrate leaching planning and cereal yield prediction within the framework of the PA to eliminate seasonal effects.

Open Access: Yes

DOI: 10.1556/0806.44.2016.056