Agricultural Environment Monitoring Research Articles

IoT-BASED AGRICULTURE ENVIRONMENT AND SECURITY MONITORING SYSTEM

Background: Agriculture is a vital part of the economy that feeds a part of the world expanding population. However, the sector faces several difficulties, including water constraints, soil degradation, and climate change. The demand for increased security and safety in agricultural activities worsens these problems. This paper suggests an IoT-based agriculture environment and security monitoring system address these issues. Aims: The main objective of this work is to develop an intelligent monitoring and automated irrigation system that minimizes water use based on individual conditions and enables real-time environmental Methods: The Arduino Uno R3 microcontroller based on Microchip ATmega328P is used to gather environmental data such as humidity, temperature, soil moisture levels. The Arduino board is integrated with a relay and RTC module to water plants at precise times. It also has a passive infrared sensor to detect intruders. ESP32 camera is also used to record the current condition of the agricultural ground automatically. A sample of reading in an interval of 1 hour is recorded. This method involves wirelessly transmitting the data to cloud-based platforms. Results: The value of the sensor at the start of a wet condition is 0. When this occurs, the motor pump turns off, and the measured value is communicated to the microcontroller through NodeMCU. The motor pump automatically turns ON and OFF when plants receive enough amount of water. Discussion: It has been observed the water pump starts as soon as the temperature threshold of 19.5 °C is achieved. It has been observed that as humidity increases, it is unnecessary to water the plants as the plants take up water vapor from the surface of the leaves under humid conditions. Conclusions: This research offers a convenient prototype model that can simultaneously measure temperature, moisture, and humidity, identify intrusion, and remotely monitor it over the internet. It was concluded that with the decrease in moisture of the soil, the plants need to be watered.

A smartphone-integrated imaging device for measuring nitrate and phosphate in soil and water samples

This research presents a smartphone-integrated imaging device to detect nitrate (NO3–) and phosphate (PO43-) in soil and water samples for agricultural input management and environmental pollution monitoring. This low-cost and field-deployable device uses a smartphone with a digital camera to take a color photograph of the extracted solution under test. The sensing principle is based on the standard colorimetric phenoldisulfonic acid and ascorbic acid methods for NO3– and PO43- in soil and water samples, respectively. A 3D printed device that houses the sensor's optical source and other optical components is coupled to the phone's built-in rear camera and turned into a compact handheld system. An android application, 'SMART NP,' is also developed to quantify the concentrations of NO3– and PO43- in soil and water samples using the Value (V) component of the Hue Saturation and Value (HSV) color space model. The results obtained with the proposed device were comparable to laboratory-grade spectrophotometer data. The limit of detection of the device for NO3– in soil, NO3– in water, PO43- in soil, and PO43- in water were calculated as 0.1 mg L-1, 0.07 mg L-1, 0.001 mg L-1, and 0.02 mg L-1, respectively, with good accuracy (≤1% bias) and precision (∼2% residual standard deviation). The device exhibited a sensitivity of 0.17 mg L-1, 0.12 mg L-1, 0.026 mg L-1, and 0.49 mg L-1 for NO3– in soil, NO3– in water, PO43- in soil, and PO43- in water, respectively. Overall, this sensing device has the potential to assist farmers or scientists in easily measuring NO3– and PO43- concentrations in soil and water media, without the need for laboratory equipment.

Natural fertility and intrinsic fragility of soils in the Brazilian Cerrado

This study aimed to evaluate the attributes of natural fertility and intrinsic fragility of the soils of Ivinhema River Basin (BHI), to subsidize agricultural development projects and environmental control and monitoring bodies. For this purpose, 62 soil samples were collected, at a depth of 0 to 20 cm, in areas of native vegetation belonging to the state of Mato Grosso do Sul – Brazil. The characteristic climate of the study area is of the humid mesothermal subtype (Cfa) without drought. The predominant vegetation is of the Cerrado type and the geological substrate is predominantly composed of the Serra Geral and Caiuá Formation. The samples were air-dried and the physical attributes (sand, silt, and clay) and chemical variables (pH H2O, CaCl2, KCl, ∆pH, Al3+, m%, H + Al, Ca2+, Mg2+, K+, CEC, SB, V%, OC, P, Cu, Fe, Mn, and Zn) were determined according to methodologies in Embrapa's soil analysis methods manual. The data obtained were evaluated by descriptive statistics and principal component analysis. The results showed a great variety of soils inside the basin, whose natural fertility was high for the Leptsol, Regosol, and Nitisol soils, and low for the Argiluvic Plinthosol, Petroplinthic Plinthosol, and Planosol soils. The sandy soils showed lower levels of organic carbon and negative surface loads, which shows less capacity to retain cations essential to plant nutrition and less retention of environmental contaminants if any. Regarding the textural fragility of the soils of BHI, it was possible to verify the high sensitivity of the soil to erosion and susceptibility to the contamination of groundwater or infiltrated water. The data shown in research can fill the gaps of knowledge and/or for adapting conservation practices of agricultural soils that are more susceptible to erosive processes, as well as for environmental control and monitoring bodies and/or studies of area recovery and maintenance of soil fertility.

Evaluation of Phytotoxicity of Common Chernozem in the Application of <i>Bacillus</i> sp. and Biochar for Stimulation of Decomposition of Winter Wheat Harvest Residues (<i>Triticum aestivum</i> L.)

Stable functioning of agricultural lands is impossible without maintaining soil fertility. However, there are often a lot of crop residues in the fields, which decompose for a long time and turn into available organic matter. To increase the rate of decomposition of crop residues of grain crops (wheat, barley and others), it is necessary to introduce biostimulants. Biostimulants are a variety of substances that stimulate the decomposition of organic substances and have a beneficial effect on the soil microbiota. The article examines the influence of Bacillus sp. on the processes of decomposition of crop residues of wheat both independently and together with biochar. The aim of the study was to evaluate the phytotoxicity of ordinary chernozem during the decomposition of crop residues of winter wheat under the influence of Bacillus sp. and biochar. To assess the ecological state of the soil, the following research methods were used: assessment of the rate of decomposition of cellulose (determination of cellulolytic activity), assessment of the ecological state of the soil (intensity of CO2 emissions, changes in the intensity of initial growth and development of winter barley (Hordeum vulgare L.)). Introduction of Bacillus sp. × 100 and the joint use of biochar and Bacillus sp. it stimulated the decomposition of cellulose up to 14–15% of the background content. Inoculation of Bacillus sp. on the biochar, it was effective already at the recommended dose both for the decomposition of the cellulose web and for restoring the ecological state of the soil, demonstrating a synergistic effect. The results obtained should be used in carrying out measures to increase soil fertility of agricultural lands and environmental monitoring of soil conditions.

基于 NB-IoT 的农业环境无线远程监测传感器

This paper describes the design and implementation of a wireless sensor based on NB-IoT (Narrow Band Internet of Things) for monitoring agricultural environmental information. The sensor is capable of real-time monitoring of four environmental parameters, including ambient temperature, relative humidity, illuminance, and CO2 concentration. In the hardware design, sensor elements are selected based on the measurement ranges and accuracies specified in agricultural environmental monitoring industry standards. The hardware circuit is designed using the BC35-G type NB-IoT module and STM32 MCU (Microcontroller Unit). In the software design, data from the environmental parameters are collected and processed by the STM32 MCU and sent to the OneNET cloud platform through the NB-IoT module. The OneNET cloud platform enables users to view the relevant environmental data collected by the sensors using mobile phones and other mobile terminals. To test the effectiveness of the developed sensors, they were tested in a glass greenhouse at Fuyang Ziqing Agricultural Technology Co., Ltd. in Anhui Province. The results demonstrate that the sensors can accurately collect the data of relevant environmental parameters and can provide stable wireless transmission of data remotely, making them suitable for practical engineering applications. In summary, this wireless remote monitoring sensor based on NB-IoT represents a significant advancement in the field of agricultural automation. The sensor's ability to accurately monitor and wirelessly transmit data in real-time provides farmers with valuable information to optimize crop growth and maximize yields.

An ultra-high sensitivity methane gas sensor based on Vernier effect in two parallel optical fiber Sagnac loops

Methane gas sensing has attracted great interest for its applications in agriculture production, industrial manufacturing, medical diagnosis, and environmental monitoring. In this paper, we proposed an ultra-high sensitivity methane gas sensor based on Vernier effect in two parallel optical fiber Sagnac loops. The reference arm contained a polarization maintaining photonic crystal fiber (PM-PCF), while sensing arm consists of a methane gas sensitive film coated PM-PCF. Vernier effect (VE) was generated and as a result the sensitivity was improved by multiple times. The finite element method (FEM) was used to assess the methane gas sensor’s sensing capabilities. According to the numerical simulation, the average sensitivity based on two parallel Sagnac loops in the methane gas concentration of 0-3.5% was 197.775 nm/%, which was 5.5 times in contrast to a single Sagnac loop. To our best knowledge, we presented the methane gas sensor based on VE in two parallel optical fiber Sagnac loops for the first time. The designed optical fiber methane gas sensor possessed the merits of ultra-high sensitivity, providing helpful guidelines for the fabrication of high-performance methane gas sensors.

Agri-Environment Atmospheric Real-Time Monitoring Technology Based on Drone and Light Scattering

The emission of particulate matter (PM) from agricultural activities, such as concentrated animal feeding, straw combustion, and mechanized harvest, is a hot issue in the sustainable development of agriculture, which has attracted more and more attention from government departments and researchers. However, the research on the transport of particulate matter in the agri-environment still lacks flexible and efficient measurement methods to obtain real-time and accurate spatial distribution data. The objective of our study is to produce a new intelligent platform for agri-environment atmospheric monitoring with high mobility, temporal and spatial resolution, and remote data transmission function to overcome the shortcomings of traditional atmospheric particulate matter monitoring stations, such as small particle size range, immovability, and high cost. Through the light scattering sensor, microcontroller, and wireless data transmission device assembled on the high-mobility drone, the platform could measure the mass concentration of PM2.5, PM10, and TSP at different spatial points in the agri-environment and transmit the measurement data to the receiving device on the ground through three modes: CLOUD, TCP, and UDP. We also developed monitoring software based on the Android platform, which could complete the connection of device and real-time monitoring of measurement data on the ground. Compared with stationary measurement devices, the biggest advantage of our mobile monitoring system is that it has the ability to measure the concentration of TSP and the vertical distribution of PM, which is very important for the research of agricultural environmental particulate matter emission characteristics. After the sensor and communication performance experiments, the sensors had high consistency in the overall change trend, and the communication accuracy rate was high. We carried out a flight measurement comparison experiment at the Wenhua Road Campus of Henan Agricultural University, and the measurement data were highly consistent with the data from the national monitoring stations. We also conducted an agri-environmental atmospheric measurement experiment in Muzhai Village and obtained the vertical distribution data of PM concentration at the nearby measuring point when the harvester was working. The results showed that after the harvester worked for a period of time, the PM2.5, PM10, and TSP concentrations reached the maximum at the altitude of 20 m at the measurement point, which were 80, 198, and 384 μg/m3, respectively, 2.64~3.10 times the particle concentration in the environment before the harvester began to work. Our new platform had high mobility, sensitive reading, and stable communication during the experiment, and had high application value in agricultural environmental monitoring.

A Data-Secured Intelligent IoT System for Agricultural Environment Monitoring

Collecting environmental information of crop growth and dynamically adjusting agricultural production has been proved an effective way to improve the total agricultural yield. Agricultural IoT technology, which integrates the information sensing equipment, communication network, and information processing systems, can support such an intelligent manner in the agricultural environment. Traditional agricultural IoT could meet the service demand of small-scale agricultural production scenarios to a certain extent. However, the emerging application scenario of the agricultural environment is becoming more and more complicated, and the data nodes of the underlying access to IoT backend system are increasing in large number, while the upper-layer applications are requiring high quality of data service. Hence, the traditional architecture-based (i.e., centralised cloud computing) IoT systems suffer from the problems such as small network coverage, data security issue, and limited power supply time while attempting to provide high-quality services at the edge of the network. Emerging edge computing offers the opportunity to solve these issues. This paper builds an intelligent IoT system for agricultural environment monitoring by integrating edge computing and artificial intelligence. We conducted an experiment to validate the proposed system considering the reliability and usability. The experimental results prove the system’s reliability (e.g., data packet loss rate is less than 0.1%). The proposed system achieves the concurrency of 500TPS and the average response time of 300 ms, which meet the practical requirements in agricultural environment monitoring.

Remote Monitoring and Management System of Intelligent Agriculture under the Internet of Things and Deep Learning

Based on the Internet of Things (IoT) technology and deep learning algorithm, a greenhouse intelligent agriculture management system was established to analyse the application value of the intelligent agriculture remote monitoring management system in the greenhouse planting industry. Based on the analysis of greenhouse planting demand and environmental factors, the intelligent agriculture monitoring system is established based on the IoT, and the greenhouse system controller is designed based on the adaptive proportion integration differentiation (PID) algorithm. The noise data removal method is established based on the furthest priority strategyk-means (FPKM) algorithm, and the greenhouse data management system is established mainly by the business platform and management platform. The data set of air temperature during the cultivation of Flammulina velutifolia in a factory from October 2020 to January 2021 was selected as the research data to analyse the ability of the IoT-based IARMM system to collect greenhouse temperature, carbon dioxide, and light data. In addition, the application of the greenhouse data management system in greenhouse data monitoring and control is analysed. The processing capability of agricultural environment monitoring data based on the FPKM algorithm is analysed. The results show that the intelligent agriculture monitoring system based on IoT and machine learning can effectively monitor the data on greenhouse temperature, carbon dioxide, light, and other environmental factors, and the greenhouse data management system can effectively ensure the normal operation of equipment and data storage. After being processed by the FPKM algorithm, outliers are identified and effectively removed. Under random seeds, the iteration times of the FPKM algorithm and thek-means algorithm are significantly different. The iteration number of the FPKM algorithm is basically stable at approximately 2 times, while the iteration number of thek-means algorithm obviously fluctuates. Based on the IoT and FPKM algorithm, the intelligent agriculture monitoring system covering the user monitoring center, data center module, and mobile phone client module is established. This work establishes a practical remote monitoring and management system for intelligent agriculture based on the IoT and machine learning algorithm, which provides a new idea for intelligent agricultural management.

Multiscale Layout and Planning of Smart Gardens in the Environment of Agricultural Internet of Things.

This paper studies the general architecture and key technologies of the Agricultural Internet of Things and summarizes the latest progress of the Internet of Things system model. On this basis, a general system architecture model suitable for the Agricultural Internet of Things is initially established, and the key technologies of the Agricultural Internet of Things are expounded to provide a reference for the in-depth application and development of the Agricultural Internet of Things. Aiming at the problem that the energy consumption of each node in the network is uneven in the process of monitoring agricultural production environment by wireless sensor network, which leads to the failure of some nodes in the network too fast, an event-driven wireless routing algorithm for agricultural production environment monitoring is proposed. By reducing the number of pieces of control information sent in the cluster, the algorithm selects the next hop forwarding node from candidate nodes according to the forwarding cost function to shorten the data transmission distance, reduce energy consumption, and improve the life cycle of the entire network. The experimental results show that the algorithm in this paper effectively avoids the waste of node energy consumption caused by the active transmission mode and at the same time better balances the overall energy consumption of the network and prolongs the life cycle of the network. The platform satisfies the needs of a local garden bureau to integrate comprehensive landscaping business information and display comprehensive landscaping information in a comprehensive, timely, and dynamic manner. At the same time, it has made useful explorations in the development and integration of landscaping business data interfaces and GIS data interfaces. All system functions of the smart garden information management platform project are reasonably designed and completely correct and basically meet the software function requirements specified in the requirements specification. Some functions were found not realized during the test. After rectification, various systems have been improved. All system interfaces of the smart garden information management platform project have reasonable layout, simple operation, and good ease of use. The smart garden information management platform project meets the business logic requirements and fulfills the requirements of the information construction of the Garden and Greening Administration. All systems of the smart garden information management platform project are simple to install and easy to operate and meet the user's requirements after installation. The system has a strict permission setting function. People with different permissions can only see the content of the fields that they have permission to access, which effectively ensures the security of the data.

Image Correction and In Situ Spectral Calibration for Low-Cost, Smartphone Hyperspectral Imaging

Developments in the portability of low-cost hyperspectral imaging instruments translate to significant benefits to agricultural industries and environmental monitoring applications. These advances can be further explicated by removing the need for complex post-processing and calibration. We propose a method for substantially increasing the utility of portable hyperspectral imaging. Vertical and horizontal spatial distortions introduced into images by ‘operator shake’ are corrected by an in-scene reference card with two spatial references. In situ light-source-independent spectral calibration is performed. This is achieved by a comparison of the ground-truth spectral reflectance of an in-scene red–green–blue target to the uncalibrated output of the hyperspectral data. Finally, bias introduced into the hyperspectral images due to the non-flat spectral output of the illumination is removed. This allows for low-skilled operation of a truly handheld, low-cost hyperspectral imager for agriculture, environmental monitoring, or other visible hyperspectral imaging applications.

Safety Training Monitoring System of Ski Resort Based on Wireless Sensor Network

With the gradual rise in China’s ski industry, skiing is now the most common sport among winter outdoor sports, which is closely related to the origin of safety issues. Based on the ski resort, training is the key to safety detection, only to ensure the safety of training personnel and to maintain the momentum of high-speed development of skiing sports for a long time. The monitoring system plays an important role in the wireless sensor network monitoring system. Common monitoring systems are used for agriculture, smart home, and outdoor environment monitoring systems, most of which are professional fields. Based on the safety of ski resorts, this paper puts forward the research of ski training safety system based on the wireless sensor. In the research of ski training detection system based on the wireless sensor network, first, the safety system of domestic ski resort is analyzed and detailed suggestions are given. Then, this paper studies the routing protocol of wireless communication technology in detail and compares the service life and energy consumption of nodes under the use of two different routing protocols in wireless sensor networks. According to the data experiment in this paper, LEACH-MH protocol has great advantages over the LEACH protocol. The LEACH-MH protocol detects 185 more rounds than the LEACH protocol in the total detection lifetime. In the detection of energy consumption of 100 m ∗ 100 m, the LEACH protocol consumes 50J in 400 rounds, while the LEACH-MH protocol consumes only 50J in 760 rounds.

RETRACTED ARTICLE: Research on data transmission model of agricultural wireless sensor network based on game theory

This article has been retracted from publication in the Taylor & Francis journal, Acta Agriculturae Scandinavica, Section B — Soil & Plant Science. Following publication, concerns were raised by multiple third-parties around the content of the special issue and the decision-making process. Following an investigation by the Taylor & Francis Publishing Ethics & Integrity team in full cooperation with the Editor-in-Chief, it was confirmed that this article included in Special Issue titled “ Envisage Computer Modelling and Statistics for Agriculture”, guest edited by Gunasekaran Manogaran was not peer-reviewed appropriately, in line with the Journal's peer review standards and policy. As the stringency of the peer review process is core to the integrity of the publication process, the Editor and Publisher have decided to retract all of the articles within the above-named Special Issue. The journal has not confirmed if the authors were aware of this compromised peer review process. The journal is committed to correcting the scientific record and will fully cooperate with any institutional investigations into this matter. The authors have been informed of this decision. We have been informed in our decision-making by our policy on publishing ethics and integrity and the COPE guidelines.

Pixel based classification for Landsat 8 OLI multispectral satellite images using deep learning neural network

In satellite image analysis, classification of objects appearing in an image is a major step of information extraction. The information acquired from the satellite image can be used to provide the solution of various remote sensing problems such as agricultural challenges, natural hazards, and environmental monitoring etc. The most of the conventional classifiers used to classify satellite images do not provide realistic classification with high accuracy. Therefore, for achieving realistic and more accurate classification of the satellite images is still a challenging task. Machine intelligence is being harnessed to solve this task. In this paper, we present a novel machine intelligence pixel based approach for multispectral satellite image classification. We have proposed a machine intelligence deep learning neural network with five hidden layers and seven training features for satellite images classification. The model is tested on four types of data sets namely three classes, four classes, five classes and seven classes. Accuracy of 99.99%, 99.96%, 99.45% and 98.03% has been obtained on four test data sets respectively. In all cases, it is observed that the proposed method provides 8.52% higher accuracy than previously proposed classifiers.

Novel Wireless Sensor Network Routing Protocol Performance Evaluation using Diverse Packet Size for Agriculture Application

As the wireless sensor networks (WSNs) progress with newer and more advanced technologies, so do the demands for them in a growing number of applications. Precision agricultural environment monitoring is one of the most prominent applications that require feasible wireless support systems, particularly in the protection and condition control of the crops. This paper focuses on the grid nodes arrangement of WSN, considering the wide dissemination of the plantation areas in the agriculture industry. Due to the different types of sensors used and their data size, the study on the impact of the varied packet size on the performance of the small and large network has been carried out using AODV and OLSR routing protocols. No significant differences in terms of performance can be seen as the packet size is varied. However, compared to the small network, more performance issues have occured in the large network, such as more packet loss, higher throughput degradation, higher energy consumption, worse unfairness, and more overhead production. The OEG routing protocol has been proposed to enhance the network performance by reducing the strain due to the saturated traffic. When solely compared to AODV, OEG routing protocol is able to enhance the network performance with at most 27% more packet delivery ratio, 31kbps more throughput, and 0.991J lesser energy consumed in the network.

Intelligent Internet of Things Technology in Agricultural Environment Monitoring

The application of the Internet of Things to precision agriculture is conducive to the intelligent and controllable aspects of agricultural production and management, is conducive to the implementation of green agricultural production methods, is conducive to the sustainable development of agriculture, and promotes the structural reform of the agricultural supply side. An intelligent greenhouse environment monitoring system is designed based on the Internet of Things technology, and a wireless network is established using the JenNet protocol to realize real-time monitoring of environmental factors such as air temperature and humidity, soil temperature and humidity, light intensity, and CO2 concentration in the greenhouse. Finally, the paper uses the time automata modelling tool UPPAAL to verify the system logic correctness and system execution timing verification on the established formal model. The results verify that the agricultural temperature control environment system network based on the intelligent Internet of Things operates stably, with high acquisition accuracy, low node power consumption, accurate feedback control, and meets the intelligent demand for greenhouse data acquisition and control.

Thoughts on building an intelligent integrated management system of agricultural environment

In modern agricultural production, environmental factors are very important. It determines not only the production cost and benefits, but also the success and difficulty of agricultural production. Agricultural environmental monitoring is the foundation of agricultural environmental management. It is vigorously developing agricultural environmental monitoring to meet the environmental needs of different varieties and planting models. Organically combining agricultural production equipment and agricultural operations is the research focus of agricultural informationization at this stage. In order to better serve the entire industry chain of agricultural forecasting, production and sales, this paper proposes to create an integrated intelligent management system that integrates pre-production, mid-production and post-production.

Non-Enzymatic Electrochemical Sensors Based on Conducting Polymer Hydrogels for Ultrasensitive Carbaryl Pesticide Detection

Pesticides play a key role in agricultural development, but pesticide residues do great harm to human health and environmental safety. Therefore, it is urgent to design a rapid and accurate pesticide monitoring method. Herein, a sensitive, label-free and non-enzymatic electrochemical sensor based on conducting polymer hydrogels, was constructed for the detection of carbaryl in aqueous solution. In this work, conducting polymer hydrogels were electrochemically prepared onto glassy carbon electrode by electrochemical copolymerization of polyaniline (PANI) and hyaluronic acid (HA). Interestingly, PANI/HA hydrogel with multiple porous microstructure and high active specific area demonstrated excellent hydrophilic and electrochemical properties, leading to the strong affinity to carbaryl pesticide. A non-enzymatic electrochemical sensor based on PANI/HA nanocomposite exhibited a linear response of 0.01–1 ng ml−1 for carbaryl, and the detection limit was 0.0034 ng ml−1. The PANI/HA modified electrode was used to determine carbaryl in the fruit samples, which showed efficient sensing ability. Therefore, the method can be popularized in the field of agricultural safety and environmental monitoring, and provides a promising avenue for the detection of pesticide residues in real samples.

Agriculture environment monitoring: rapid soil fertility evaluation by means of near infrared spectroscopy

In agricultural practices, the development of environmental controlling programs is essential in maintaining soil fertility. It should be monitored constantly in real time situation by predicting soil properties such as nutrients and mineral contents. The main purpose of this presented paper is employ the near infrared spectroscopy (NIRS) technique in determining nitrogen (N) and magnesium (Mg) content of agricultural soil rapidly and simultaneously. Near infrared spectra data of soil samples were obtained by acquiring absorbance data in wavelength range from 1000 to 2500 nm using a portable sensing device NIR with a photodiode array detector. Spectra data were enhanced using mean normalization approach to improve prediction accuracy. Further, prediction models were developed by means of partial least square regression (PLSR) followed by cross validation. The results showed that both soil fertility properties (N and Mg) can be predicted by NIRS with maximum correlation coefficient (r) were 0.93 and 0.91 for N and Mg respectively. It may conclude that NIRS technique was able to be used in agriculture environment monitoring especialy to predict soil fertility properties.

RANCANG BANGUN PERTANIAN STROBERI BERBASIS INTERNET OF THINGS

Technological developments have been utilized in various fields of science, includingagriculture. Technology support in agriculture has been proven to be able to provide betterproduction results. In this study, an IoT-based agricultural environmental monitoring systemwas developed. The system was built using Raspberry Pi as a microcontroller and dataprocessing center, equipped with a moisture sensor and a DHT 11 temperature sensor. Thissystem was applied to a laboratory-scale strawberry farm. The system works automatically toregulate the temperature and humidity of the plant environment. If the temperature andhumidity of the strawberry plants do not meet the standards, the pump will automatically waterto keep the strawberry plants at the appropriate temperature and humidity. The system is alsoequipped with a notification feature so that strawberry farmers can obtain information throughtelegram media when the temperature of the strawberry plants is hot and the soil of thestrawberry plants is dry. This tool is also equipped with a webcam camera as an additionalfeature that serves to detect the level of ripeness of the strawberries in terms of the color of thefruit. The camera will detect the color of the strawberry, and if the strawberry is red, thestrawberry is categorized as ripe, and the farmer will get a notification via telegram in the formof a picture that the strawberry is ready to be harvested.