SmartGreen IoT-Enhanced Sustainable Ecosystem for microgreen

The integration of technology into agriculture has revolutionized traditional farming practices, leading to innovative solutions for sustainable food production. In this context, the Smart Greens project emerges as an ambitious endeavor, leveraging the power of theInternet of Things (IoT) and machine learning to cultivate microgreens within a sophisticated, sustainable ecosystem. Microgreens, characterized by their compact size, rapid growth, and rich nutritional content, have gained prominence in the culinary world and health-conscious markets. However, optimizing their cultivation demands precise control over environmental conditions such as temperature, humidity, light exposure, and soil moisture. Conventional approaches often struggle to strike the delicate balance required for optimal growth while minimizing resource usage The Smart Greens initiative addresses these challenges by fusing IoT technologies and machine learning algorithms. The IoT infrastructure integrates an array of sensors strategically placed within the cultivation environment. These sensors continuously capture real-time data, providing an intricate view of the conditions influencing microgreen growth. Simultaneously, machine learning algorithms analyze this influx of data, employing pattern recognition and predictive models to discern the intricate relationships between environmental variables and microgreen development. Through iterative learning, these algorithms adapt, fine-tune, and optimize growth parameters, aiming to create an ideal ecosystem for diverse microgreen varieties. This convergence of IoT and machine learning not only streamlines cultivation processes but also fosters sustainability. By dynamically adjusting growth conditions based on data-driven insights, Smart Greens seeks to maximize yield efficiency while minimizing resource consumption.The project aspires to not only enhance microgreen production but also serve as a model for sustainable agriculture practices in broader contexts.

The Smart Greens project pioneers a paradigm shift in microgreen cultivation by leveraging a sophisticated amalgamation of cutting-edge technologies—IoT and Machine Learning—to address pressing challenges in traditional agricultural practices. At the forefront are the IoT sensors strategically deployed throughout the cultivation environment. These sensors serve as the primary data collection nodes, meticulously capturing real-time environmental parameters critical to microgreen growth, encompassing moisture levels, temperature variations, humidity, and ambient lighting. Their role lies in incessantly acquiring data, andproviding the foundational input necessary for precise monitoring and control.

Adjacent to the sensor nodes, the diagram illustrates a centralized IoT gateway. This pivotal block serves as the nexus for data aggregation and transmission. It seamlessly integrates the data streams from the sensors, acting as a conduit for relaying this information to a centralized server or cloud infrastructure for further processing and analysis

Moreover, the diagram likely features the incorporation of Machine Learning algorithms within the system architecture. These algorithms play a vital role in data processing, interpreting the voluminous data streams obtained from the sensors. They contribute by discerning patterns, making predictive models, and facilitating informed decision-making to dynamically regulate and optimize the growth environment for microgreens. This integration of Machine Learning models signifies a sophisticated layer within the architecture, enabling autonomous adjustments and refinements to the cultivation environment based on data-driven insights, thereby ensuring continual enhancement and precision in growth conditions. The block diagram Fig 1 prominently showcases various essential blocks, each contributing uniquely to the system's functionality

The diagram prominently showcases various essential blocks, each contributing uniquely to the system's functionality. At the forefront are the IoT sensors strategically deployed throughout the cultivation environment. These sensors serve as the primary data collection nodes, meticulously capturing real-time environmental parameters critical to microgreen growth, encompassing moisture levels, temperature variations, humidity, and ambient lighting. Their role lies in incessantly acquiring data, andproviding the foundational input necessary for precise monitoring and control.

Adjacent to the sensor nodes, the diagram illustrates a centralized IoT gateway. This pivotal block serves as the nexus for data aggregation and transmission. It seamlessly integrates the data streams from the sensors, acting as a conduit for relaying this information to a centralized server or cloud infrastructure for further processing and analysis.

BLOCK DIAGRAM

The block diagram in Fig 2 for the Smart Greens project unfolds a comprehensive system designed to revolutionize microgreen cultivation through the amalgamation of IoT and Machine Learning technologies. Strategically placed IoT sensors form the initial layer, continuously gathering real-time data on environmental factors such as moisture, temperature, humidity, and ambient lighting crucial for microgreen growth. These sensors feed their data into a centralized IoT gateway, acting as a central hub for data aggregation and transmission. The gateway seamlessly integrates information from the sensors and facilitates the transmission of this data to a centralized server or cloud infrastructure for further analysis. The incorporation of Machine Learning algorithms forms a sophisticated layer within the architecture, playing a pivotal role in processing the extensive data streams. These algorithms discern patterns, create predictive models, and contribute to informed decision-making. The system's dynamic adjustment and optimization capabilities, guided by Machine Learning insights, ensure continual enhancement and precision in microgreen growth conditions. The block diagram, depicted in Fig 2, visually encapsulates the interconnected functionalities of the various components, showcasing the innovative and integrated nature of the Smart Greens cultivation system.

APPLICATION

The Smart Greens project assumes paramount importance in the socioeconomic landscape by directly tackling global challenges associated with food security, sustainability, and economic development. Harnessing cutting-edge technologies such as IoT and machine learning, Smart Greens contributes significantly to socioeconomic progress. Its precision cultivation techniques promise increased crop yields and minimal waste, aligning with global efforts to enhance food security. The project's commitment to sustainable agriculture practices, optimizing resource usage and promoting energy conservation, positions it as a beacon for environmentally friendly farming. Beyond the environmental impact, Smart Greens introduces economic empowerment by leveraging autonomous operations, potentially reducing labor dependency and creating opportunities for job creation in technology and agricultural innovation. As a symbol of technological advancement in agriculture, Smart Greens not only enhances the sector's reputation but also attracts interest and investment in technology-driven solutions for global challenges. Furthermore, the project serves as a platform for knowledge transfer and education, fostering a skilled workforce by disseminating insights into advanced agricultural technologies. In essence, SmartGreens stands as a comprehensive solution intertwining agricultural innovation, environmental sustainability, and socioeconomic advancement for a more resilient and prosperous society.

We achieved the successful development of a comprehensive system by integrating various sensors. This efficient system ensures the seamless upload of sensor data to the cloud through Firebase integration. We also completed a user-friendly Flutter application(fig 3) with an intuitive interface, featuring live monitoring capabilities for moisture levels, light intensity, temperature, and humidity levels. This innovative app not only allows users to monitor these conditions in real time but also empowers them to make manual adjustments for optimal cultivation.

CONCLUSION

SmartGreens is a pioneering initiative that harnesses IoT and ML technologies to revolutionize microgreen cultivation. By enabling autonomous operation and precise environmental control, the project aims to increase crop yield while reducing human intervention. This not only directly tackles global food security challenges but also promotes sustainability.

SmartGreens stands out as a hopeful example of technology and environmental responsibility coexisting harmoniously. Its integration of advanced technologies signifies a positive shift towards a more sustainable and efficient future in agriculture. By addressing key issues like resource optimization and climate change resilience, SmartGreens sets a precedent for the agricultural sector.

As a beacon of hope, SmartGreens demonstrates that technology can play a crucial role in enhancing productivity without compromising our ecosystems. It reflects the possibility of achieving high agricultural output while maintaining environmental balance. In the face of challenges related to feeding a growing population and climate uncertainties, SmartGreens offers a model for sustainable, tech-driven solutions.

Ultimately, SmartGreens embodies an optimistic outlook, emphasizing that innovation guided by environmental consciousness can lead to a prosperous and balanced coexistence. It serves as a reminder that transformative solutions are within reach when technology is applied with a mindful approach to our planet's well-being.

.

APPENDIX

PROGRAM CODE: (Not complete)

#include "DHT.h"

#include <FB_Const.h>

#include <FB_Error.h>

#include <FB_Network.h>

#include <FB_Utils.h>

#include <Firebase.h>

#include <FirebaseFS.h>

#include <Firebase_Client_Version.h>

#include <Firebase_ESP_Client.h>

#include <MB_NTP.h>

#include <Arduino.h>

#include <WiFi.h>

#include <Firebase_ESP_Client.h>

//Provide the token generation process info.

#include "addons/TokenHelper.h"

//Provide the RTDB payload printing info and other helper functions.

#include "addons/RTDBHelper.h"

#define WIFI_SSID "Galaxy m51"

#define WIFI_PASSWORD "aswin001"

// Insert Firebase project API Key

#define API_KEY "AIzaSyBwH01d4eynxAzFQP3s7NSM_PpkvHpgTQ0"

// Insert RTDB URL

#define DATABASE_URL "https://cooling-system-8c431-default-rtdb.asia-southeast1.firebasedatabase.app"

const int DHT11PIN = 16;

const int MOIST = 4;

FirebaseData fbdo;

FirebaseAuth auth;

FirebaseConfig config;

DHT dht(DHT11PIN, DHT11);

unsigned long sendDataPrevMillis = 0;

int intValue;

float floatValue;

bool signupOK = false;

int moist;

void setup() {

Serial.begin(115200);

dht.begin();

WiFi.begin(WIFI_SSID, WIFI_PASSWORD);

Serial.print("Connecting to Wi-Fi");

while (WiFi.status() != WL_CONNECTED) {

Serial.print(".");

delay(300);

}

Serial.println();

Serial.print("Connected with IP: ");

Serial.println(WiFi.localIP());

Serial.println();

/* Assign the api key (required) */

config.api_key = API_KEY;

/* Assign the RTDB URL (required) */

config.database_url = DATABASE_URL;

/* Sign up */

if (Firebase.signUp(&config, &auth, "", "")) {

Serial.println("ok");

signupOK = true;

}

else {

Serial.printf("%s\n", config.signer.signupError.message.c_str());

}

/* Assign the callback function for the long running token generation task */

config.token_status_callback = tokenStatusCallback; //see addons/TokenHelper.h

Firebase.begin(&config, &auth);

Firebase.reconnectWiFi(true);

}

void loop()

{

int humi = dht.readHumidity();

int temp = dht.readTemperature();

int sens_read= analogRead(4);

// Write humidity

if (Firebase.RTDB.setInt(&fbdo, "humidity", humi))

{

Serial.println("PASSED");

Serial.println("PATH: " + fbdo.dataPath());

}

else

{

Serial.println("FAILED");

Serial.println("REASON: " + fbdo.errorReason());

}

// Write temperature

if (Firebase.RTDB.setInt(&fbdo, "temperature", temp))

{

Serial.println("PASSED");

Serial.println("PATH: " + fbdo.dataPath());

}

else

{

Serial.println("FAILED");

Serial.println("REASON: " + fbdo.errorReason());

}

// Write moisture

if (Firebase.RTDB.setInt(&fbdo, "moisture", sens_read))

{

Serial.println("PASSED");

Serial.println("PATH: " + fbdo.dataPath());

}

else

{

Serial.println("FAILED");

Serial.println("REASON: " + fbdo.errorReason());

}

delay(5000);

}

REFERENCE

C. Gnauer, H. Pichler, C. Schmittner, M. Tauber, K. Christl, J. Knapitsch and M. Parapatits , "A recommendation for suitable technologies for an indoor farming framework," Elektrotech. Inftech, p. 370–374, 2020.

• C. Gnauer, H. Pichler, C. Schmittner, M. Tauber, K. Christl, J. Knapitsch and M. Parapatits , "A recommendation for suitable technologies for an indoor farming framework," Elektrotech. Inftech, p. 370–374, 2020.

W. Rankothge, P. Kehelella, D. Perera, B. Kanchana, K. Madushan, and R. Peiris, “IOT Based Smart Microgreen Sprouter,”

• W. Rankothge, P. Kehelella, D. Perera, B. Kanchana, K. Madushan, and R. Peiris, “IOT Based Smart Microgreen Sprouter,”

N. S. Abu, W. M. Bukhari, C. H. Ong, M. N. Sukhaimie, S. Wibowo, and A. M. Kassim, “Automated Agricultural Management Systems Using Smart-Based Technology,” Int. J. Emerg. Technol. Adv. Eng., vol. 12, no. 5, pp. 123–131, 2022, doi: 10.46338/ijetae0522_14.

• N. S. Abu, W. M. Bukhari, C. H. Ong, M. N. Sukhaimie, S. Wibowo, and A. M. Kassim, “Automated Agricultural Management Systems Using Smart-Based Technology,” Int. J. Emerg. Technol. Adv. Eng., vol. 12, no. 5, pp. 123–131, 2022, doi: 10.46338/ijetae0522_14.

22 International Conference on Information Management and Technology (ICIMTech) | 978-1-6654-5090-4/22/$31.00 ©2022 IEEE | DOI: 10.1109/ICIMTECH55957.2022.991501 “IoT Architectural Design for Microgreens Cultivation“

• 22 International Conference on Information Management and Technology (ICIMTech) | 978-1-6654-5090-4/22/$31.00 ©2022 IEEE | DOI: 10.1109/ICIMTECH55957.2022.991501 “IoT Architectural Design for Microgreens Cultivation“

N. Watjanatepin and C. Boonmee, “Which Color of Light from the Light Emitting Diodes is Optimal for Plant Cultivation?,” The Technical Writer’s Handbook. Science and Technology Journal, Thailand, vol.25, pp. 158-176,2017

• N. Watjanatepin and C. Boonmee, “Which Color of Light from the Light Emitting Diodes is Optimal for Plant Cultivation?,” The Technical Writer’s Handbook. Science and Technology Journal, Thailand, vol.25, pp. 158-176,2017

A. Chidburee, A. Namin, K. Sansupa and T. Kaipet, “ Effect of blue/red/white LEDs combination on growth of eucalyptus (Eucalyptus camaldulensis Dehnh.) tissue in vitro,” Khon Kaen Agr. J. Khon Kaen, vol. 42, pp. 409-414, 2014.

• A. Chidburee, A. Namin, K. Sansupa and T. Kaipet, “ Effect of blue/red/white LEDs combination on growth of eucalyptus (Eucalyptus camaldulensis Dehnh.) tissue in vitro,” Khon Kaen Agr. J. Khon Kaen, vol. 42, pp. 409-414, 2014.

J M. Fakaim, K. Banlupholsakul and K. Khongseeprai “ Case Study of Automatic Plants Watering System Using Solar Energy for Rice Breeding Plan,” Journal of Industrial Technology, Ubon Ratchathani, vol. 1, pp. 55-66, 2016.

• J M. Fakaim, K. Banlupholsakul and K. Khongseeprai “ Case Study of Automatic Plants Watering System Using Solar Energy for Rice Breeding Plan,” Journal of Industrial Technology, Ubon Ratchathani, vol. 1, pp. 55-66, 2016.

J. Yothatip, P. Sunakorn and P. Boonkorkaew, “Study of Growing Indoor Plants using Artificial Light,” The 14th National Kasetsart University Kamphaeng Saen Conference .

• J. Yothatip, P. Sunakorn and P. Boonkorkaew, “Study of Growing Indoor Plants using Artificial Light,” The 14th National Kasetsart University Kamphaeng Saen Conference .

Cui, L., Yang, S., Chen, F. et al. A survey on application of machine learning for Internet of

• Cui, L., Yang, S., Chen, F. et al. A survey on application of machine learning for Internet of

Things. Int. J. Mach. Learn. & Cyber. 9, 1399–1417 (2018)

Maduranga, M.W.P. and Abeysekera, R. (2020) ‘Machine learning applications in IOT based agriculture and Smart Farming: A Review’, International Journal of Engineering Applied Sciences and Technology, 04(12), pp. 24–27.

• Maduranga, M.W.P. and Abeysekera, R. (2020) ‘Machine learning applications in IOT based agriculture and Smart Farming: A Review’, International Journal of Engineering Applied Sciences and Technology, 04(12), pp. 24–27.