KMITL Expo 2026 LogoKMITL 66th Anniversary Logo

Artificial intelligence of things system for monitoring and controlling irrigation using weather information

Abstract

This research focuses on the design and development of a prototype Artificial Intelligence of Things (AIoT) system for monitoring and controlling irrigation using weather information. The system consists of four main components: 1) Weather Station – This component includes various sensors such as air temperature, relative humidity, wind speed, and sunlight duration, among others, to collect real-time weather data. 2) Controller Unit – This unit is equipped with machine learning algorithms or models to estimate the reference evapotranspiration (ETo) and calculate the plant’s water requirement by integrating the crop coefficient (Kc) with other plant-related data. This enables the system to determine the optimal irrigation amount based on plant needs automatically. 3) User Interface (UI) and Display – This section allows farmers or users to input relevant information, such as plant type, soil type, irrigation system type, number of water emitters, planting distance, and growth stages. It also provides a display for monitoring and interaction with the system. 4) Irrigation Unit – This component is responsible for controlling the water supply and managing the irrigation emitters to ensure efficient water distribution based on the calculated requirements.

Objective

การเปลี่ยนแปลงสภาพอากาศของโลกทวีความรุนแรงขึ้นอย่างต่อเนื่อง สถานการณ์ดังกล่าวส่งผลกระทบ โดยตรงต่อภาคการเกษตร โดยเฉพาะในประเทศไทยที่มีแนวโน้มเผชิญกับปัญหาการขาดแคลนน้ำและความ ผันผวนของปริมาณน้ำฝน ซึ่งส่งผลต่อทั้งปริมาณและคุณภาพของผลผลิตทางการเกษตรโดยตรง ทั้งนี้ การบริหารจัดการน้ำในภาคเกษตรกรรมของประเทศไทยยังคงเผชิญกับข้อจำกัดหลายประการ เกษตรกรส่วนใหญ่ยังคงพึ่งพาประสบการณ์ส่วนตัวในการให้น้ำพืช ซึ่งอาจนำไปสู่การใช้น้ำที่ไม่มีประสิทธิภาพ เช่น การให้น้ำมากเกินความจำเป็นหรือน้อยเกินไปจนส่งผลกระทบต่อผลผลิต หรืออาจนำไปสู่ปัญหา เช่น การแตกใบอ่อน การร่วงของดอก และมีผลผลิตที่ไม่ได้คุณภาพ (Togneri et al., 2023) ในขณะที่ข้อมูลทาง วิชาการที่สามารถช่วยให้การบริหารจัดการน้ำมีความแม่นยำขึ้น เช่น ค่าอัตราการใช้น้ำของพืชอ้างอิง (Evapotranspiration: ETo) และค่าสัมประสิทธิ์พืช (Kc) กลับเข้าถึงได้ยาก เนื่องจากมีความซับซ้อนในการ คำนวณ อีกทั้งข้อมูลที่มีอยู่มักเป็นข้อมูลเฉลี่ยรายจังหวัดซึ่งไม่สามารถนำไปใช้ได้อย่างมีประสิทธิภาพในระดับ ฟาร์ม โครงการนี้จึงมุ่งเน้นไปที่การพัฒนาระบบปัญญาประดิษฐ์สำหรับการติดตามและควบคุมการให้น้ำพืชอัจฉริยะ โดยอิงข้อมูลสภาพอากาศซึ่งจะช่วยแก้ไขข้อจำกัดของเกษตรกรไทยในการเข้าถึงข้อมูลที่ ถูกต้องและการบริหารจัดการน้ำที่แม่นยำ

Other Innovations

Handheld Mercury Meter

คณะวิทยาศาสตร์

Handheld Mercury Meter

This work presents the fabrication of the handheld meter for potentiometric detection of Hg (II). The meter was constructed based on using an ion-sensitive field-effect transistor (ISFET) platform. The developed meter provides high accuracy and precision (%Recovery was in the range of 92.55 - 109.32 and %RSD was 2.38). It was applied to the analysis of cosmetic samples. The results by the developed electrode were not significantly different at a 95% confidence level compared to the results by using ICP-OES.

Read more
A Comparison of The Performance of Machine Learning Methods on Time Series Data Using Lagged Time Intervals

คณะวิทยาศาสตร์

A Comparison of The Performance of Machine Learning Methods on Time Series Data Using Lagged Time Intervals

This special problem aims to compare the performance of machine learning methods in time series forecasting using lagged time periods as independent variables. The lagged periods are categorized into three groups: lagged by 10 units, lagged by 15 units, and lagged by 20 units. The study employs four machine learning methods: Decision Tree (DT), Random Forest (RF), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM). The time series data simulated as independent variables diverse including characteristics: Random Walk data, Trending data, and Non-Linear data, with sample sizes of 100, 300, 500, and 700. The research methodology involves splitting the data into 90% for training and 10% for testing. Simulations and analysis are performed using the R programming language, with 1,000 iterations conducted. The results are evaluated based on the average mean squared error (AMSE) and the average mean absolute percentage error (AMAPE) are calculated to identify the best performing method. The research findings revealed that for Random Walk data, the best performing methods are Random Forest and Support Vector Machine. For Trend data, the best performing methods are Random Forest. For Non-Linear data, the best performing methods are Support Vector Machine. When tested with real-world data, the results show that for the Euro-to-Thai Baht exchange rate, the best methods are Random Forest and Support Vector Machine. For the S&P 500 Index in USD, the best performing methods are Random Forest. For the Bank of America Corp Index in USD, the best performing methods are Support Vector Machine.

Read more
WHAT IS THE CURRENT ENERGY EXPENDITURE OF HOUSEHOLDS IN THAILAND ?

คณะวิทยาศาสตร์

WHAT IS THE CURRENT ENERGY EXPENDITURE OF HOUSEHOLDS IN THAILAND ?

The purpose of this study was to examine and analyze the factors influencing household energy expenditures in Thailand. With sample group of 57,600 households. The findings reveal that the majority of the sample population is male, with an average age of 54.31 years, and most are married. The majority have an education level of primary or secondary school and are primarily Own-account worker (without employee), Private company employee or engaged in other job. In terms of social characteristics, the average household size is 2.71 people. Most residences are located in the Central, Northeastern, and Northern regions with similar proportions, followed by the Southern region and Bangkok, respectively. Most type of dwelling in detached houses, with materials of construction being cement or brick, followed by half concrete and wood. Regarding tenure, almost own dwelling and land, with an average of 2.88 rooms per household. Electricity is available in all households, with an average of 2.30 vehicles per household and an average of 22 electrical appliances per household. Regarding economic characteristics, most respondents have government/state enterprise welfare and receive benefits from the government programs. The majority have never borrow money from government funds. The average communication services of respondents amount to 788.46 THB, while the average household debt stands at 4,760.74 THB. At a significance level of 0.05, the factors influencing household energy expenditures in Thailand include gender, education level, marital status, job, household size, residential region, type of dwelling, material of construction, tenure, number of rooms, number of vehicles, number of electrical appliances, welfare of medical services, receive benefits from the government programs, borrow money from government funds, communication services, and household debt. However, age does not affect household energy expenditures in Thailand. The results of multiple linear regression analysis indicate that six quantitative independent variables—communication services, number of household electrical appliances, number of vehicles in the household, household debt, number of rooms, and household size—explain variations in household energy expenditures, with an Adjusted R Square value of 0.561.

Read more