An approach, an algorithm, and an intelligent management decision support system are proposed for predicting the time fund for the implementation of plant protection. They are based on database formation and weather knowledge from the OpenWeatherMap service for individual countries and their regions. Based on computer modeling, they provide the formation of databases and knowledge for a given country or its region, taking into account the characteristics of natural, climatic, and production conditions. The proposed intelligent management decision support system systematically analyzes variable agrometeorological components and their impact on the time frames of relevant works in the plant protection project. The developed intelligent management decision support system made it possible to forecast the time fund for plant protection given natural, climatic, and production conditions. A model of climatically permissible time fund for the protection of plants during the day of June, described by Weibull distribution, is substantiated. The results of the obtained studies can be used by managers of agricultural enterprises during project management. In particular, during the process of forecasting the duration of plant protection projects. The developed intelligent management decision-making support system provides further research on the prediction of the plant protection implementation time fund and the justification of its models in different countries and their regions
Agricultural enterprises involved in the production of plant products experience losses every year and lose a significant amount of crops due to weeds, pests, and diseases. According to the FAO (Food and Agriculture Organization), more than 40% of crops globally are lost to pest activity each year, i.e. approximately 37% - before harvest and 9% - during storage. Adjusted losses from loss of crop yields are estimated at $30 billion. At the same time, the losses caused by diseases in agricultural plants amount to 25 billion dollars [1-3]. The protection of plants is carried out to prevent and prevent crop damage from pests. At the same time, the content and time planning of the work on the protection of the plant is carried out in advance. Qualitative planning of the mentioned processes can be carried out only with a known fund of time for the implementation of plant protection [4-6]. Forecasting the time frame for the implementation of plant protection is a complex management task. This is due to the influence of many variable factors of the agrometeorological component on the performance of plant protection, which requires time-consuming calculations using probability theory and mathematical statistics [7-9]. The above indicates that there is a need to confirm the characteristics of timely fund forecasting for the implementation of plant protection, as well as for the development of computerbased application software due to the presence of time-consuming calculations. This is done based on modeling the agrometeorological component of the plant protection system.
Many works are devoted to solving problems of time pool forecasting for work in various applied fields, taking into account their characteristics [10-12]. They are based on developed mathematical models and methods which are partially idealized and take into account the specifics of specialized production conditions.
There are several scientific publications [13-14] that justify the need to develop a general toolkit for predicting working time irrespective of the specifics of the application domain. It is because of this that specifics of the agrometeorological component of plant protection systems are not fully taken into account.
Available publications [15-17], which relate to forecasting in various branches of production, deserve special attention. Some of them are related to crop production and take into account the specifics of the industry. However, they cannot be fully used to predict the timing of plant protection implementation because they do not take into account the specifics of the agrometeorological component of the plant protection system.
There are several scientific works [18-20] in which the authors discuss the peculiarities of agrometeorological conditions for various systems of agricultural production. They are used in intelligent driving decision support systems. However, regarding the consideration of agrometeorological component features in intelligent decision support systems, they are not for plant protection. In particular, existing intelligent decision support systems are designed for strategic and tactical planning of work performance [21-24].
The task of operational forecasting of the fund of time for the implementation of plant protection requires taking into account the natural, climatic, and production conditions of individual countries and their regions and conducting relevant research, which ensures the creation of an adequate database. and knowledge that is the basis of an intelligent decision support system for predicting the timing of plant protection under given conditions.
Therefore, the existing approaches to plant production planning decision-making and intelligent support systems do not fully take into account the natural-climatic and production-changing conditions of individual countries and their regions, which determine the timely foundation for the implementation of plant protection [25-28]. This is one of the main reasons for poor management decisions in the operational planning of plants, as well as for crop losses due to the timely reduction of pests and plant diseases.
Currently, there is a scientific and applied task to substantiate the approach to predicting the time fund of plant protection, as well as due to the need for time-consuming calculations, the development of application software based on computer modeling of the agrometeorological component [29-32]. About the mechanized protection system of plants of individual countries and their regions. Solving this scientific and applied problem has both scientific and practical importance.
The purpose of this work is to develop an approach to predicting the terms of work in plant protection projects and an algorithm for an intelligent management decision support system. To achieve the goal, the following tasks must be solved: 1. Develop an approach and algorithm for forecasting work in plant protection projects, taking into account the climatic conditions of the region; 2. To Develop an intelligent decision-making support system for predicting working hours in plant protection projects and, based on it, justify the model of the permissible duration of plant protection.
During the season of action of harmful objects on crops of certain crops, there is a time interval during which the protection of plants is possible or impossible. With this in mind, the naturally defined time fund for plant protection is the time (in hours) during which the technological operation of crop spraying can be carried out [33-35].
The formation of a naturally permissible time fund for the implementation of plant protection takes into account several climatic factors that reflect the meteorological conditions of a particular region: fT xo f (O, R, V , T , I ) , (1) where O – is the presence of precipitation, R – is the presence of dew; V – wind speed; T – air temperature; I – time of day (light or dark).
The peculiarity of the protection of plants by spraying is their high sensitivity to weather conditions and the state of the surface layer of the atmosphere [36]. So, rainy weather, fog, increasing heat flows, and wind belong to unfavorable conditions that can completely neutralize the efficiency of processing and cause negative ecological consequences. Adverse weather conditions significantly affect the rate of pesticide application and the environmental friendliness of plant protection processes.
In case of wind speed of more than 4 m/s, the sprayed mixture of the boom sprayers will be carried away from the field, polluting the environment. At air temperatures above +25 °C, drops of the working fluid evaporate quickly. During excessive humidity and precipitation, the working fluid is washed away from the plants, reducing the efficiency of cultivation and polluting the soil.
It is known that in some countries there is a constantly changing state of the atmosphere, which is determined by an alternating stochastic sequence of naturally acceptable and unacceptable time for the implementation of protection of plants, as in terms of individual calendar days. and specific calendar period (plant development phase) [37].
The determination of the naturally permissible time fund for the implementation of the protection of plants is carried out according to the course of weather conditions and can be graphically displayed on the calendar axis of the start time and duration of action of individual agrometeorological factors, both separately and collectively (Figure 1).
Precipitation (short-term or long-term and its intensity) plays a key role in the formation of the naturally permissible time fund for the protection of plants, which determines the waiting time after its completion (Drying time of soil and plants).
The action of agrometeorological factors during the period of growing crops (April-August) is characterized by probability [38]:
P A mA , (2) n where n – is the total number of cases investigated; mA – the number of occurrences that correspond to a certain event.
According to the statistical data of the reporting period (April-August [39]), the number of events that met a certain condition (exceeding the permissible values of limiting factors) on a separate calendar day. The total number of days studied was determined. Certain regularities can be observed in nature, for example, if there is dew, there is no rain, and vice versa, the time exceeding the permissible air temperature is observed only in the middle of the day (when the sun is relatively at its highest point. to the horizon).
Along with the increase in the probability of the maximum average daily air temperature, due to the increase in the height of the sun above the horizon, the probability of exceeding the allowable values of wind gusts decreases simultaneously, but at the same time the occurrence of dew increases. On the other hand, it can be safely said that precipitation is slightly dependent on other agrometeorological factors (average daily air temperature, dew point, excessive wind flow), as evidenced by the correlation coefficient (Table 1).
Therefore, the simultaneous consideration of agrometeorological factors is quite difficult. However, without this, it is impossible to objectively substantiate the effective complex of plant defense mechanisms by spraying. The derived regularities are the first step towards modeling the action of these factors and probabilistic estimation of the time pool naturally allowed for spraying plants.
The established regularities of the occurrence and progression of individual agrometeorological factors in time are the first step in the way of reflecting the naturally determined time frames of plants for the implementation of protection of plants by spraying. It is assumed that such agrometeorological factors as mean daily air temperature (correlation coefficient – 0.931), excessive wind speed (correlation coefficient – 0.981), and dew (correlation coefficient – 0.882) depend on calendar time. The simulation model takes into account the particularity of agrometeorological conditions in each region, and can objectively demonstrate the necessity the need for technical means of protection of plants by spraying.
To predict the pool of plant protection times during which weather conditions are favorable for plant protection by spraying, statistical data on weather conditions are collected from the OpenWeatherMap service for individual countries or their regions.
Based on the above, the following conditions were considered favorable for the implementation of technological processes of protection of plants: air temperature +5°... +25°C; absence onf precipitatio and fog; wind speed 0...4 m/s; Lack of thermal flow in the surface layer of the atmosphere.
A block diagram and algorithm for predicting the climatically acceptable time fund for the implementation of protection of plants by spraying on a separate day was developed based on substantiated methods and models of the characteristics of natural-climatic and production conditions [40]. The block diagram consists of 19 blocks (Figure 2).
The first block is intended for entering initial data into the computer memory: length of daylight hours; the presence of dew; air temperature; Wind speed and precipitation.
Blocks 2-9 are intended for the formation of agrometeorological numerical series and for checking the correspondence of their values.
Blocks 10-13 are designed to perform protection of plants to determine the climatically acceptable time fund by spraying on a separate day, respectively, according to the length of daylight hours; the presence of dew; air temperature; Wind speed, and precipitation.
Blocks 14-17 are designed to carry out the protection of plants by spraying on a separate day to check compliance with the values of the climatically acceptable time fund.
The 18th block aims to check the state of completeness of the implemented implementation and to determine the climatically permissible time for the implementation of protection of plants by spraying on a separate day.
Block 19 is intended for displaying the results of calculations.
Based on the disclosure of the content of the blocks shown in the block diagram, an algorithm for computer modeling of the agrometeorological component was developed and a forecast of the climatically permissible time fund for the implementation of plant protection by spraying on a separate day was made. The proposed intelligent management system for forecasting the fund of time required for plant protection is developed in Python 3.9, the working window of which is shown in Figure 3.
The probability of favorable conditions for the protection of plants is greatest in the morning and evening hours. Considering this, it is advisable to divide the work into half shifts (3 hours in the morning and 3 hours in the evening). Half-shift duration is set in hours (by default, half-shift duration is 3 hours).
The developed intelligent management decision-making support system for plant protection implementation time fund forecasting performs the necessary calculations and provides climatically acceptable time fund determination and visualization for plant protection implementation. A separate day for a given country and its region.
According to the Mann-Whitney criterion, the suitability of the proposed intelligent management decision support system for the conditions of Sokal United Territorial Community (Ukraine), was tested. At the same time, the deviation between the predicted plant protection implementation time limit and the actual value does not exceed 4%, which proves its adequacy.
Based on the application of the developed intelligent management decision support system for time fund forecasting, a computer simulation of the agrometeorological component was carried out in the conditions of the western forest-steppe of Ukraine on different days of the plant protection season.
The conducted study provided for the construction of the histogram and theoretical distribution curve of the climatically permissible time fund for the protection of plants during the day of June (Figure 4).
The statistical processing of the received data on the fund of protection of plants by the climate during the day made it possible to determine the numerical characteristics, as well as to justify the model (Figure 4), which is described by the Weibull distribution. with the differential function:
The main statistical features of the climate-suitable time distribution for plant protection in June are mathematical expectation estimate - 8.7 hours; dispersion - 11.2 hours; mean square deviation 3.43 hours. A reasonable approach to forecasting the time fund for the implementation of plant protection and the algorithm and the intelligent management decision support system developed on its basis provide a high-quality forecast of the time fund for the implementation of plant protection. Features of the agrometeorological component of individual countries and their regions. 6. Conclusions
1. The proposed approach, algorithm, and intelligent management decision support system for predicting the duration of work in plant protection projects are based on the formation of a database and knowledge of weather from the OpenWeatherMap service for individual countries and their regions. The main feature of the proposed approach is that databases and knowledge are formed for a given country or its region, based on computer modeling, taking into account the characteristics of natural, climatic, and production conditions. This ensures that the set of variable agrometeorological components of the plant protection system and their influence on the forecast fund of the time of execution of the respective works are systematically considered. The proposed approach fully takes into account the peculiarities of the subject area. It provides a high-quality database and knowledge formation, as well as the creation of an intelligent system that provides accelerated and high-quality management decisions related to predicting the duration of work in plant protection projects.
2. Based on the application of the developed intelligent management decision support system, the duration of work in plant protection projects and given natural-climatic and production conditions was determined. This substantiated the model of the climatically acceptable time fund for Plant Protection Day in June. The obtained model is described by the Weibull distribution with the main statistical characteristics: estimation of mathematical expectation – 8.7 hours; dispersion – 11.2 hours; estimate of root mean square deviation – 3.43 hours. The obtained research results can be used by managers of agricultural enterprises during the management processes of predicting the duration of work in plant protection projects. 7. References [1] T. Shi, Y. Liu, X. Zheng, H. Liu, H. Huang, Recent advances in plant disease severity assessment using convolutional neural networks. Scientific Reports 13(1) (2023) 2336. [2] M. Nayagam, B. Vijayalakshmi, K. Somasundaram, C. Yogaraja, P. Partheeban, Control of pests and diseases in plants using IOT Technology. Measurement: Sensors 26 (2023) 100713. [3] R. King, B. Buer, T.G.E. Davies, R. Nauen, L. Field, The complete genome assemblies of 19 insect pests of worldwide importance to agriculture. Pesticide Biochemistry and Physiology 191 (2023) 105339. [4] A. Tryhuba, V. Boyarchuk, I. Tryhuba, S. Francik, and M. Rudynets, Meth od and software of planning of the sub stantial risks in the projects of production of raw ma terial for biofuel. CEUR Workshop Proceedings 2565 (2020) 116-129. [5] V. Boyarchuk, I. Tryhuba, Forecas ting of a Lifecycle of the Projects of Pro duction of Biofuel Raw Materials With Con sideration of Risks, in International Conference on Advanced Trends in Information Theory (ATIT), 2019, pp. 420-425. [6] P. Lub, S. Berezovetskyi, R. Padyuka and R. Chubyk, Information-analytical support of project management processes with the use of simulation modeling methods. CEUR Workshop Proceedings 3109 (2022). 53-57. [7] P. Lub, V. Pukas, A. Sharybura, R. Chubyk and O. Lysiuk, The information technology use for studying the impact of the project environment on the timelines of the crops harvesting projects.
CEUR Workshop Proceedings 2851 (2021) 324-333. [8] A. Tryhuba, R. Ratushny, I. Horodetskyy, Y. Molchak, V. Grabovets, The configurations coor dination of the projects products of develop pment of the community fireextinguishing systems with the project environment. CEUR Workshop Proceedings 2851 (2021) 238-248. [9] A. Tryhuba, I. Tryhuba, O. Ftoma and O. Boyarchuk, Method of quantitative evaluation of the risk of benefits for investors of fodder-producing cooperatives, in: 14th International Scientific and Technical Conference on Computer Sciences and Information Technologies (CSIT), 2019, 3, pp. 55-58. [10] J. Babayev, M. Vukomanovic, S. Bushuyev, I. Achkasov, Managing Projects Portfolio in Complex Environments Based On Fuzzy Situational Networks. CEUR Workshop Proceedings, 3295 (2022) 107-116. [11] O. Bashynsky, Coordina tion of dairy works hops projects on the community territory and their project envi ronment, in: International Scientific and Technical Conference on Computer Sciences and Information Technologies, 2019, 3, pp. 51-54. [12] L. Chernova, A. Zhuravel, L. Chernova, N. Kunanets, O. Artemenko, Application of the Cognitive Approach for IT Project Management and Implementation. International Scientific and Technical Conference on Computer Sciences and Information Technologies, 2022, 2022November, pp. 426-429. [13] А. Tryhuba, V. Boyarchuk, I. Tryhuba, Study opfacthoef tihme volume of investments in agrarian projects on the risk of the ir value. CEUR Workshop Proceedings 2851 (2021). [14] I. Kondysiuk, O Bashynsky, V. Dembitskyi, I. Myskovets, Formation and risk assessment of stakeholders value of motor transport enterprises development projects, in: International Scientific and Technical Conference on Computer Sciences and Information Technologies, 2021, 2, pp. 303-306. [15] O. Bashynsky, T. Hutsol, A. Rozkosz, O. Prokopova, Justification of Parameters of the Energy Supply System of Agricultural Enterprises with Using Wind Power Installations, in: E3S Web of Conferences, 154, 2020. [16] N. Koval, I. Kondysiuk, V. Grabovets, V. Onyshchuk, Forecasting the fund of time for performance of works in hybrid projects using machine training technologies. CEUR Workshop Proceedings 2917 (2021) 196-206. [17] А. Tryhuba, V. Boyarchuk, I. Tryhuba, O. Ftoma, R. Padyuka, M. Rudynets, Forecasting the ri of the resource demand for dairy farms basing on machine learning. CEUR Workshop Proceedings 2631 (2020). [18] A. Tryhuba, R. Ratushny, O. Bashynsky and V. Ptashnyk, Planning of Territorial Location of Fire-Rescue Formations in Administrative Territory Development Projects. CEUR Workshop Proceedings 2565 (2020) 18-20. [19] A. Tryhuba, O. Bashynsky, I. Kondysiuk, N. Koval and L. Bondarchuk, Conceptual model of management of technologically integrated industry development projects, in: 15th International Scientific and Technical Conference on Computer Sciences and Information Technologies (CSIT), 2020, 2, pp. 155-158. [20] B. Batyuk, M. Dyndyn, Coordination of Configurations of Complex Organizational and Technical Systems for Development of Agricultural Sector Branches. Journal of Automation and Information Sciences 52(2) (2020) 63-76. [21] V. Piterska, O. Kolesnikov, D. Lukianov, K. Kolesnikova, V. Gogunskii, Develop ment of the Markovi an model for the life cycle of a pro ject’s benefits. Eastern-European Journal of Enterprise Technologies 5 (4(95)) (2018) 30-39. [22] O. Verenych, C. Wolff, S. Bushuyev, O. Bondar and O. Voitenko, Hybrid Competencies Model for Managing Innovation Projects. CEUR Workshop Proceedings 3295 (2022) 25-37. [23] S. Bushuyev, N. Bushuyeva, D. Bushuiev, V. Bushuieva, Cognitive Rea diness of Managing Infra structure Projects Driving by SMAR Tification, in: European Technology and Engineering Management Summit, E-TEMS 2022 - Conference Proceedings, 2022, pp. 196-201. [24] O. Kovalchuk, O. Zachko and D. Kobylkin, Criteria for intellectual forming a project tea ms in safety oriented system, in: 17th International Scientific and Technical Conference on Computer Sciences and Information Technologies (CSIT), 2, 2022, pp. 430-433. [25] W. Zhuo, S. Fang, X. Gao, Q. Wu, J. Huang, Crop yield prediction using MODIS LAI, TIGGE weather forecasts and WOFOST model: A case study for winter wheat in Hebei, China during 2009-2013. International Journal of Applied Earth Observation and Geoinformation 106 (2022) 102668. [26] A. Tryhuba, V. Boyarchuk, I. Tryhuba, et al., Model of assessment of the risk of investing in the projects of production of biofuel raw materials, in: 15th International Scientific and Technical Conference on Computer Sciences and Information Technologies (CSIT), 2, 2020, pp. 151-154. [27] A. Bondar, S. Bushuyev, V. Bushuieva, S. Onyshchenko, Complementary strategic model for managing entropy of the organization. CEUR Workshop Proceedings 2851 (2021) 293-302. [28] S. Bushuyev, D. Bushuiev, V. Bushuieva, Interaction Multilayer model of Emotional Infection with the Earn Value Method in the Project Management Process, in: 15th International Scientific and Technical Conference on Computer Sciences and Information Technologies, CSIT 2020 Proceedings, 2020, 2, pp. 146-150. [29] H. Olekh, K. Kolesnikova, T. Olekh and O. Mezentseva, Environmental Impact Assessment Procedure As The Implementation Of The Value Approach In Environmental Projects. CEUR Workshop Proceedings 2851 (2021) 206-216. [30] S. Bushuyev, O. Verenych, The Blended Mental Space: Mobility and Flexibility as Characteristics of Project/Program Success, in: 13th International Scientific and Technical Conference on Computer Sciences and Information Technologies (CSIT), 2018, 2, pp. 148-151. [31] O. Kovalchuk, D. Kobylkin, O. Zachko, Digitalization of HR-management processes of projectoriented organizations in the field of safety. CEUR Workshop Proceedings 3295 (2022) 183-19. [32] N. Kunanets, L. Sokur, V. Dobrovolska, S. Lytvyn, Project Acti vities of Shevchenko National Preser ve in Infor mational Society, in: International Scientific and Technical Conference on Computer Sciences and Information Technologies, 2021, 2, pp. 423-426. [33] D. Kobylkin, O. Zachko, R. Ratushny, Models of content mana gement of infrastructure projects mono templates under the in fluence of project changes. CEUR Workshop Proceedings 2851 (2021) 106-115. [34] R. Nebesnyi, N. Kunanets, R. Vaskiv, N. Veretennikova, Formation of an IT Project Team in the Context of PMBOK Requirements, in: International Scientific and Technical Conference on Computer Sciences and Information Technologies, 2021, 2, pp. 431-436. [35] S. Chernov, S. Titov, L. Chernova, N. Kunanets, V. Piterskad, Y. Shcherbynac and L. Petryshyn, Efficient algorithms of linear optimization problems solution. CEUR Workshop Proceedings 2851 (2021). [36] O. Bashynsky, I. Garasymchuk, O. Gorbovy, et al., Research of the variable natural potential of the wind and energy energy in the northern strip of the ukrainian carpathians, in: 6th International Conference : Renewable Energy Sources (ICoRES 2019). E3S Web of Conferences, 154, 06002, 2020. [37] V. Boyarchuk, N. Pavlikha, Risk-Adapted model of the lifecycle of the technologically integrated programs of dairy cattle breeding, in: International Scientific and Technical Conference on Computer Sciences and Information Technologies, 2021, 2, pp. 307-310. [38] M. Bacci, O.A. Idrissa, C. Zini, A.A. Sitta, V. Tarchiani, Effectiveness of agrometeorological services for smallholder farmers: The case study in the regions of Dosso and Tillaberi in Niger.
Climate Services 30 (2023) 100360. [39] J. Gao, L. Liu, L. Guo, W. Hou, S.Wu, The effects of climate change and phenological variation on agricultural production and its risk pattern in the black soil area of northeast China. Journal of Geographical Sciences 33(1) (2023) 37-58. [40] F. Michel, Agroclimate Information and World Food Perspectives. Agroclimate Information for Development Reviving the Green Revolution, 2022, pp. 18-24.