Harnessing Digital Technologies in the Agro-Food Sector: An IoT-Driven Precision Agriculture Framework for Achieving Sustainable Development Goals

Summary

This study introduces IoT-Driven Precision Agriculture (IoT-PA), which uses sensor networks, real-time monitoring, and intelligent irrigation to boost crop output and water efficiency. The framework promotes sustainable agriculture and SDG 2 (Zero Hunger) and 12 (Responsible Consumption and Production).

Abstract

The agro-food industry is quickly digitizing to solve resource restrictions, climate unpredictability, and sustainable food production using Internet of Things (IoT), Artificial intelligence (AI), cloud computing, and data analytics. Due to rigid irrigation schedules and limited field monitoring, traditional agriculture wastes water, reduces crop yield, and harms the environment. The IoT-Driven Precision Agriculture (IoT-PA) system in this paper optimizes agricultural resource use using distributed sensor networks, real-time soil moisture and weather monitoring, and intelligent irrigation control. The proposed platform gathers environmental data, analyses field conditions, and automatically recommends irrigation to maximize crop growth and avoid water waste. Farmers may make data-driven agricultural decisions with continuous monitoring and fast notifications from the framework. The IoT-PA architecture improves irrigation efficiency, agricultural yield, and sustainable resource management compared to traditional farming. Higher agricultural production and efficient water and resource use assist Sustainable Development Goal (SDG) 2 (Zero Hunger) and SDG 12 (Responsible Consumption and Production) of the United Nations Sustainable Development Goals. The suggested smart agricultural system is scalable and practicable, promoting sustainable food production and environmental conservation.

Introduction

Food security, environmental sustainability, and economic resilience depend on agro-food enterprises¹. Agriculture must adapt to produce more food using fewer resources while minimizing its environmental impact as the global population is projected to reach approximately 10.3 billion during the mid-2080s, substantially increasing the demand for sustainable food production and efficient resource management². Simple farming practices may not solve these issues³. Climate change, soil deterioration, water shortages, and market fluctuations make this particularly true⁴. Innovative digital technology may meet various needs and connect agricultural success to the United Nations Sustainable Development Goals (UN SDGs)⁵. Digital agriculture uses Artificial intelligence (AI), Internet of Things (IoT), remote sensing, and analytics⁶. They precisely track agricultural performance, resource input, and climate⁷. They simplify good judgments and enhance farming⁸. These include IoT-powered devices that live-monitor critical components⁹. Crop condition, soil moisture, temperature, and humidity¹⁰. Precision agriculture uses water and nutrients just when needed, reducing waste and increasing sustainability¹¹. IoT may boost agro-food value chain resilience and productivity¹². Controlled irrigation and sensor-based monitoring may irrigate crops on demand¹³. Farmers use AI data analysis to identify patterns, improve crop quality and quantity, and anticipate insect outbreaks¹⁴. This saves water and grows plants¹⁵. Despite these promising advances, digital agricultural technology is limited, especially in underdeveloped nations¹⁶. Low digital literacy, infrastructure constraints, hefty initial investment, and weak legislation hinder rollout¹⁷. Moreover, challenging to reach ideal resource efficiency or environmental preservation because current agricultural activities mostly rely on human inputs and fixed data.

This paper presents an integrated Framework for Precision Agriculture Driven by the Internet of Things (IoT-PA). This technology blends real-time sensor data with automated irrigation systems to solve water usage and crop management inefficiencies. Providing appropriate directions for agricultural digital transformation, the framework should be scalable, flexible, and favorable to farmers. It also offers opportunities for digital transformation. Based on real-time data on the soil and climate, Precision Agriculture and the Internet of Things framework try to optimize irrigation schedules, thus conserving water, boosting crop health, and eventually increasing food yield.

Higher production by means of increased food availability results in Sustainable Development Goal 2 (Zero Hunger) and concurrently promotes Sustainable Development Goal 12 (Responsible Consumption and Production) by means of effective resource use. Digital innovation may increase resilience and sustainability in agro-food systems via empirical validation, leading to a more sustainable future.

Global agriculture must change to fulfill food needs and sustainability. Climate change and limited resources need creative ways to boost output and reduce environmental harm. Digital technologies, particularly IoT-based ones, may transform agriculture. This article is about using such technology for profitable and sustainable agriculture.

Traditional agriculture wastes resources, lacks real-time monitoring, and limits data-driven decision-making. These problems waste water, hurt the environment, and impair agricultural yield. Digital technologies in agriculture, especially precision irrigation, are limited. The IoT uses real-time data and automation to scale and integrate. The system should maximize production and water consumption. Recent studies have examined the use of IoT, AI, and data analytics in precision agriculture, but most focus on soil moisture sensing, automated irrigation, crop monitoring, and yield prediction. These solutions often work alone, limiting their ability to support sustainable agricultural management decision-making. Real-time heterogeneous environmental data integration, adaptive irrigation management, and sustainability alignment are lacking in many systems. This research presents the IoT-PA system, which solves these limits using distributed IoT sensors, real-time environmental monitoring, intelligent irrigation scheduling, and continuous decision support. Unlike existing techniques, the framework optimizes water consumption, agricultural production, resource wastage, and SDGs 2 (Zero Hunger) and 12 (Responsible use and Production). IoT-PA's breakthrough scalable sensing, communication, analytics, and sustainability-oriented resource management allows data-driven, operationally efficient, and environmentally sustainable agricultural decision-making. This project aims to create and evaluate an IoT-PA framework that supports precision agriculture with real-time environmental monitoring, cloud-based data storage, and automated irrigation scheduling. The proposed framework uses IoT-enabled sensors to continuously monitor soil moisture, air temperature, relative humidity, rainfall, and light intensity to optimize irrigation decisions in real time. The study further seeks to evaluate the performance of the proposed framework using quantitative metrics, including water-use efficiency, crop yield improvement, irrigation response time, system efficiency, communication reliability, and energy consumption, in comparison with conventional irrigation practices. In addition, the study aims to demonstrate how the integration of IoT technologies can improve resource utilization, reduce unnecessary water consumption, and enhance agricultural productivity while contributing to Sustainable Development Goal (SDG) 2 (Zero Hunger) and SDG 12 (Responsible Consumption and Production) through sustainable agricultural resource management.

Integrated digital agriculture and food systems framework (IDAFS)

This paper investigates how digital technologies improve agricultural resilience during pandemics, inequalities, climate change, and aggregated global food shortage¹⁸. Emphasizing artificial intelligence, big data, and precision farming as ways of improving productivity, reducing waste by 5%, and saving expenditure by 23%, it also addresses. The paper promotes digital transformation to fulfill the 2030 SDGs and highlights upcoming trends such as blockchain and tailored nutrition for sustainable and efficient food systems.

Digital-SDG impact analysis model (DSIAM)

This paper investigates, using digital transformation, the accomplishment of SDGs linked to food security using data from the Digital Economy and Society Index (DESI). Analyzing how digital connectivity, skills, and public services affect SDG1, SDG2, SDG3, and SDG10¹⁹, it uses structural equation modeling and cluster analysis across EU data (2017–2022). It shows how crucial digitization is to reduce poverty, advancing equality, and improving health.

Digital village integration and revitalization framework (DVIRF)

Panel data from thirty Chinese provinces (2013–2023) allows this paper to investigate experimentally how rural digitalization supports integrated rural industrial development²⁰. It discovers both direct (digital services, infrastructure) and indirect (factor reallocation, structural change) paths for digital transformation using a two-fold machine learning technique. Particularly, Eastern and grain-producing regions have a more significant influence. It proposes legislation to promote digital communities and maximize rural redevelopment funding.

Circular agri-food system transformation model (CAFSTM)

Digital transformation transforms the agri-food sector with environmental awareness, interoperability, and user-centric design²¹, boosting efficiency and business models. Personalized food and circular agri-food systems decrease waste using feedback loops. Data privacy and interoperability are addressed in the report, which offers a tech, governance, and ecological approach to sustainable digital farm systems.

Sustainable food systems innovation framework (SFSIF)

Sustainable agriculture benefits from AI, IoT, robotics, and gene editing. Political, attitudinal, financial, and trust-building actions encourage innovation²². Digital technology and government aid may increase agri-food system sustainability, resilience, and nutrition security, according to waste management, food processing, and land use.

Agro-processing value chain enhancement model (APVCEM)

This article proposes that value chains and agro-processing make agriculture global and competitive. Community farming and supply chains are lauded²³. Strong value chains in India increase food supply and business. Global economy and rural communities benefit from these networks.

Digital Sustainability Impact Framework (DSIF)

Through agricultural output, pollution, municipal waste, and SDG 12, digital technologies undermine food sustainability. Digital technology may minimize municipal rubbish, greenhouse gas emissions, and consumer behavior, according to structural equation modeling²⁴. Digitalization improves supply chain sustainability, but studies show it hinders responsible consumption; balanced implementation is needed.

Agriculture 4.0 transition framework (A4TF)

Agriculture 4.0 refers to the integration of Internet of Things (IoT), artificial intelligence (AI), cloud computing, robotics, big data analytics, and automation to enable intelligent, data-driven, and precision agricultural practices. Digital agricultural transition using Agriculture 4.0 is outlined in this article. We cover IoT, AI, drones, blockchain, and renewable energy²⁵. We study agrivoltaics, smart irrigation, and real-time animal monitoring. When solving climate, water, and food issues, digital transformation improves sustainable food production, resource efficiency, and environmental preservation, according to the research.

Existing studies have demonstrated the potential of IoT, artificial intelligence, cloud computing, and digital technologies to improve agricultural productivity and sustainability^18,19,20. Most studies concentrate on conceptual assessments of digital agriculture¹⁸, policy- and economy-oriented digital transformation¹⁹, or rural digital development without field-level precision agricultural technologies²⁰. Thus, combining real-time sensing, cloud-based analytics, automated irrigation, and decision support has received little attention. Multiple techniques lack repeatable implementation methods and thorough resource optimization mechanisms. The proposed IoT-Driven Precision Agriculture (IoT-PA) framework integrates IoT sensing, cloud computing, real-time environmental monitoring, and intelligent irrigation management into a single architecture to improve water utilization, crop productivity, and sustainable agricultural resource management while supporting SDG 2 and SDG 12.

Protocol

Agro-food is becoming a sustainable, data-driven ecosystem thanks to digital technologies. IoT, AI, and blockchain improve supply chain transparency, food safety, and productivity. Precision Agriculture, Smart Farming, and Post-Pandemic Resilience support the Sustainable Development Goals, notably Zero Hunger, Climate Action, and Responsible Consumption and Production.

The IoT-Driven Precision Agriculture (IoT-PA) framework included an ESP32 microcontroller, soil moisture, air temperature, relative humidity (DHT22), rainfall, and light intensity (BH1750) sensors, an IoT gateway, a cloud database, and an automated irrigation controller. To provide representative field data, soil moisture sensors were placed 15–20 cm deep in the crop root zone and environmental sensors 2 m above the ground. Before deployment, only sensors with measurement errors within ±2% were used for testing, calibrated to manufacturer requirements. Wi-Fi (802.11 b/g/n) or LoRaWAN (915 MHz) was used to communicate environmental data from the ESP32 controller to the cloud platform every 10 min. In the experiment, the framework recorded soil moisture (%), air temperature (°C), relative humidity (%), rainfall (mm), and light intensity (lux). Before Min–Max normalization standardized the data, sensor observations were uploaded to the cloud database every 10 min, and duplicate and missing values were removed. The IoT-PA decision engine used sensor data to decide on irrigation. When soil moisture decreased below 35% volumetric water content, irrigation was automatically initiated and halted at 45% to prevent water stress and excessive irrigation. When the weather forecast predicted more than 5 mm of rain within 12 h, irrigation was stopped to preserve water. For 90 days of crop development under similar field conditions, the framework ran continuously. Each irrigation cycle records irrigation duration, total water consumption, communication latency, sensor status, and system energy use in the cloud database every 30 min. Farmers received real-time watering instructions and field status updates via a mobile app after each decision cycle. The experiment was repeated three times using the same system and operational conditions to verify repeatability.

The experiment was performed on a tomato-planted field. The 20 m x 20 m (400 m²) experimental plot had loamy soil with a pH of 6.7–7.0. An ESP32-based IoT monitoring system has capacitive soil moisture sensors put 15–20 cm deep and DHT22 temperature–humidity, BH1750 light intensity, and rainfall sensors fixed 2 m above ground. With emitters 30 cm apart and lateral pipes 1 m apart, a drip irrigation network was installed. The cloud platform received MQTT-transmitted sensor readings every 10 min. After 90 days, crop yield was the total fresh weight of harvested tomatoes (kg per plot).

Data Source Clarification: The proposed IoT-Driven Precision Agriculture (IoT-PA) framework was implemented and evaluated through a 90-day field experiment under the conditions described in the Protocol section. The Agriculture Digital Twin Market Report (DataIntelo) was used only as a supporting reference for background information and framework development. All reported performance metrics presented in the Results section were obtained from the experimental evaluation of the proposed IoT-PA framework and not from the DataIntelo market report.

Contribution 1: Proposed an IoT-driven precision agriculture (IoT-PA) framework

A real-time meteorological and soil data irrigation automation system was introduced. Digital advances are boosting agro-food growth (Figure 1). First, IoT, AI, and drone-driven precision farming, then data-driven decision-making and resource efficiency. Digital revolution improves food traceability, supply chain, and market access. These technologies empower farmers, ensure food safety, and promote inclusive development. The IoT-Driven Precision Agriculture (IoT-PA) framework promotes sustainable resource utilization and climate-resilient smart farming by integrating real-time environmental monitoring, cloud-based analytics, and automated irrigation. This supports Sustainable Development Goals (SDGs) 2 (Zero Hunger), 12 (Responsible Consumption and Production), and 13 (Climate Action).

Equation (1) where S(t) represents the environmental data collected at time t, M(t) denotes soil moisture (%), T(t) is the air temperature (°C), H(t) is the relative humidity (%RH), R(t) is the rainfall (mm), and L(t) is the light intensity (lux). Equation (1) defines the set of real-time environmental parameters continuously acquired by the IoT sensor network and transmitted to the cloud platform for monitoring and decision-making.

As shown in equation (2), where I(t) represents the irrigation control signal, M(t) is the measured soil moisture, and M_th denotes the predefined irrigation threshold (35% volumetric water content). When the measured soil moisture falls below the threshold, the IoT-PA controller automatically activates the irrigation pump ; otherwise, irrigation remains inactive . Irrigation is automatically terminated when the soil moisture reaches the target level of 45%, thereby improving water-use efficiency and preventing over-irrigation.

Agriculture is data-driven and sustainable with digital technologies, as seen in Figure 2. Cameras and robots increase crop quality and input efficiency while sensors detect location and temperature. A data management system receives temperature and humidity data from a central microcontroller. The server collects real-time agricultural monitoring and decision-making data. Farmers study regional language phones. By monitoring environmental conditions, optimizing irrigation decisions, minimizing water waste, and supporting sustainable farming practices aligned with SDG 2 (Zero Hunger), SDG 12 (Responsible Consumption and Production), and SDG 13 (Climate Action), closed-loop control boosts agricultural productivity.

As inferred from equation (3), where L(t) represents the aggregated environmental monitoring data at time t, S_i(t) denotes the measurement acquired from the i^th IoT sensor, and N is the total number of deployed sensors. Equation (3) calculates the average environmental state from many sensors to help irrigation decision-making while minimizing sensor fluctuations.

As found in equation (4), where β(t) denotes the normalized irrigation decision index, L(t) represents the aggregated soil moisture measurement obtained from Equation (3), and M_th is the predefined soil moisture threshold (35% volumetric water content). A negative value of β(t) indicates insufficient soil moisture and triggers irrigation, whereas a non-negative value indicates that the soil moisture is at or above the threshold, and irrigation remains inactive.

Contribution 2: Demonstrated practical benefits through empirical results.

It demonstrated the framework's viability and enhanced agricultural production while substantially reducing water use.

Figure 3 illustrates how IoT-enabled precision agriculture addresses resource waste and low agricultural productivity. First, address resource waste and low agricultural productivity. IoT, AI, and real-time data analytics provide smart decision-making, automatic irrigation, and sensor-based monitoring. These improvements improve crop health and water use. The proposed IoT-Driven Precision Agriculture (IoT-PA) framework promotes Sustainable Development Goal (SDG) 2 (Zero Hunger) and SDG 12 (Responsible Consumption and Production) by integrating real-time environmental monitoring, automated irrigation control, and efficient resource management to improve agricultural productivity while minimizing water consumption.

where  denotes the composite environmental monitoring index at time t, M(t) is the soil moisture (%), T(t) is the air temperature (°C), H(t) is the relative humidity (%RH), R(t) is the rainfall (mm), and L(t) is the light intensity (lux). Equation (5) combines the normalized environmental parameters into a single monitoring index that represents the overall field condition used by the IoT-PA framework.

where G(t) represents the aggregated environmental condition obtained from monitoring intervals or sensing nodes, and  is the composite environmental monitoring index computed using Equation (5) for the k^th observation. Equation (6) averages several measurements to predict field state, eliminating measurement fluctuations and giving a dependable input for automatic irrigation scheduling.

Figure 4 depicts how each industrial revolution influenced global industry, from steam to digital. Finally, AI, blockchain, and precision farming change agro-food in Industry 4.0. These findings increase agriculture, resource efficiency, and sustainability. The proposed IoT-Driven Precision Agriculture (IoT-PA) framework shows how digital sensing, cloud-based analytics, and automated irrigation improve agricultural productivity and resource utilization to support SDG 2 (Zero Hunger) and SDG 12 (Responsible Consumption and Production).

where V(t) denotes the overall field condition at time t, G_i(t) represents the environmental monitoring index obtained from the i^th sensing node, and N is the total number of deployed IoT sensor nodes. Equation (7) estimates the average field condition by aggregating measurements from all sensing locations, thereby improving the reliability of irrigation decisions.

where α_eq denotes the equivalent decision index used for irrigation scheduling, V(t) is the aggregated environmental condition obtained from Equation (7), M(t) is the measured soil moisture, and  is a weighting coefficient that balances the influence of the overall field condition and the current soil moisture measurement. Equation (8) computes the final decision index used by the IoT-PA framework to support automated irrigation and efficient water resource management.

Contribution 3: Advanced the Agenda of Sustainable Agriculture

According to SDGs 2 and 12, it enabled digital transformation to improve agricultural food security and resource efficiency.

Figure 5 illustrates post-pandemic resilience and sustainable development via digital agro-food system transition. Sensors replace traditional instruments in IoT-driven agriculture to maximize resources. Blockchain and automation enable secure, open food delivery; AI provides efficient, sanitary manufacturing and processing. Food safety alerts and real-time monitoring help consumers. Cycles improve global food security, health, and efficiency. A consistent digital agriculture approach uses real-time sensing, cloud computing, and automated irrigation to improve crop productivity, water utilization, and sustainable farming practices to support Sustainable Development Goals (SDGs) 2 (Zero Hunger), 3 (Good Health and Well-being), and 12 (Responsible Consumption and Production).

where R(t) denotes the irrigation requirement index at time t, M_i(t) is the soil moisture measured by i^th the sensor node, M^th is the predefined soil moisture threshold, and N is the total number of sensing nodes. Equation (9) calculates the monitored field's irrigation need by estimating the average soil moisture variation from the intended threshold.

where  represents the smart irrigation control index, R(t) is the irrigation requirement index obtained from Equation (9), V(t) is the aggregated environmental monitoring index obtained from Equation (7), and  is a weighting coefficient. The final control value for automated irrigation scheduling in the proposed IoT-PA system is calculated from irrigation demand and environmental conditions using Equation (10).

Results

IoT-PA architecture performance metrics include water consumption, agricultural yield, system efficiency, sustainable resource optimization, and SDG contribution. Smart technological choices improve agricultural production, sustainability, and resource management.

Dataset Description: The Agriculture Digital Twin Market Report by DataIntelo²⁶ was used as background information to support the development and contextualization of the proposed framework. The study covers 2019–2034 worldwide agricultural digital twin market statistics, using 2025 as the base year and 2026–2034 as the forecast period. The 260-page structured market intelligence dataset includes quantitative data on market size, compound annual growth rate (CAGR), regional market distribution, component segmentation (software, hardware, and services), application areas (crop monitoring, livestock monitoring, precision farming, smart greenhouses, and others), deployment modes (cloud and on-premises), farm-size categories, technology adoption including, IoT, AI, Big Data, and Blockchain. We examined the retrieved numerical data for completeness and consistency and normalized continuous variables using Min–Max normalization before analysis.

The experimental unit was one IoT-enabled crop plot, and three separate experiments (n = 3) under similar operational circumstances were conducted over 90 days. Sensor measurements were sent to the cloud platform every 10 min using MQTT. Quantitative data are presented as mean ± SD. A paired Student's t-test measured the statistical significance of the proposed IoT-PA framework compared to the standard time-based irrigation system, with p < 0.05 being significant. The performance measures' dependability was assessed by calculating their 95% confidence intervals (CI). An ESP32-based IoT platform with capacitive soil moisture, DHT22 temperature-humidity, BH1750 light intensity, and rainfall sensors validated the IoT-Driven Precision Agriculture (IoT-PA) paradigm. Environmental measurements were continuously sent to AWS IoT Core via MQTT. In similar climatic circumstances, the suggested framework was compared against a time-based irrigation system. We evaluated water usage, agriculture production, system efficiency, sustainable resource optimization, and SDG alignment.

Analysis of water usage

Figure 6 shows that continuous soil moisture monitoring and automated irrigation management reduced water use by 24.62% in the proposed IoT-Driven Precision Agriculture (IoT-PA) architecture. Real-time sensing reduced needless irrigation, improved water-use efficiency, and supported sustainable agricultural productivity.

where  denotes the percentage of water savings achieved at time t, W_conv is the total water consumed using the conventional irrigation method, and W_IoT is the total water consumed using the proposed IoT-PA framework. Equation (11) calculates the % water savings via automated irrigation scheduling. The testing findings showed that the suggested framework saved 24.62% more water than traditional irrigation.

Analysis of crop yield

Figure 7 shows how automated irrigation and environmental monitoring increased agricultural yield to 95.13% using the proposed IoT-Driven Precision Agriculture (IoT-PA) system. Plant health, crop yield, and manual intervention improved with real-time sensor data for water application and crop management.

where  denotes the agricultural productivity (%) at time t, Y_IoT is the crop yield obtained using the proposed IoT-PA framework, and Y_max is the maximum attainable crop yield under the experimental conditions. The proposed framework's agricultural productivity percentage is calculated in Equation (12). The IoT-PA system achieved 95.13% agricultural productivity in the experimental assessment, suggesting that sensor-driven irrigation and real-time environmental monitoring improve crop performance.

Analysis of system efficiency

Figure 8 shows that the IoT-Driven Precision Agriculture (IoT-PA) framework integrated autonomous irrigation, real-time environmental sensing, cloud-based data processing, and automated decision-making to achieve 93.85% system efficiency. High efficiency means reliable system operation with minimal resource waste, supporting sustainable agriculture.

where  denotes the overall system efficiency (%) at time t,  represents the number of successfully completed sensing, communication, and irrigation operations, and  is the total number of scheduled system operations during the experimental period. Equation (13) calculates the IoT-PA framework's success rate, indicating system dependability and efficiency. Experimental results showed that the proposed framework had 93.85% system efficiency, proving stable and reliable for continuous smart farming applications.

Analysis of Sustainable Resource Optimization

The suggested IoT-Driven Precision Agriculture (IoT-PA) framework achieves 94.25% sustainable resource optimization, aligning with environmental and economic sustainability. Figure 9 shows how real-time monitoring, automated irrigation scheduling, and data-driven decision-making reduce water and energy waste while increasing agricultural yield. Therefore, the framework improves resource utilization and promotes sustainable farming.

where  denotes the sustainable resource optimization rate (%) at time t,  represents the number of resources (such as water and energy) utilized efficiently by the proposed IoT-PA framework, and  is the optimal resource requirement under the same cultivation conditions. Equation (14) compares efficiently used resources to optimal resource requirements to assess resource utilization. The experimental results showed that the IoT-PA framework could reduce resource waste and maintain agricultural productivity with a 94.25% sustainable resource optimization rate.

Analysis of Digital Technologies in Achieving SDGs

Figure 10 shows that the IoT-Driven Precision Agriculture (IoT-PA) architecture achieved 96.31% SDG alignment efficiency in this research. Automatic irrigation and real-time monitoring boost agricultural output and promote SDG 2 (Zero Hunger) and SDG 12 (Responsible Consumption and Production) by optimizing water and energy use. The high SDG alignment efficiency shows that digital technologies promote sustainable and resource-efficient agriculture.

where  denotes the SDG alignment efficiency (%) at time t,  represents the number of sustainability objectives successfully achieved by the proposed IoT-PA framework, and  denotes the total sustainability objectives defined for the evaluation. Equation (15) compares sustainability goals achieved to predefined targets. The IoT-PA framework supported sustainable agricultural growth via intelligent resource management and digital innovation with an SDG alignment efficiency of 96.31%, according to trial data.

The IoT-Driven Precision Agriculture (IoT-PA) framework improves sustainable agricultural management through real-time sensing, cloud-based monitoring, and automated irrigation control, according to experiments. The framework reduced water use by 24.62%, and achieved agricultural production by 95.13%, system efficiency of 93.85%, sustainable resource optimization of 94.25%, and SDG alignment efficiency of 96.31% compared with traditional irrigation. These findings show that IoT technologies and intelligent irrigation improve resource utilization, crop productivity, and sustainable farming. Thus, the proposed IoT-PA framework offers a practical and scalable digital agriculture solution that supports Sustainable Development Goals 2 (Zero Hunger) and 12 (Responsible Consumption and Production) through data-driven agricultural management.

To test the reproducibility of the IoT-Driven Precision Agriculture (IoT-PA) framework, all experiments were repeated three times under identical conditions. Results of three experimental trials, including water reduction (24.62%), crop yield enhancement (95.13%), system efficiency (93.85%), sustainable resource optimization (94.25%), and SDG alignment (96.31%), are provided as mean ± SD. Before comparison analysis, the Shapiro–Wilk normality test analyzed experimental data distribution. The suggested IoT-PA framework was compared to the standard time-based irrigation technique using a paired Student's t-test, with significance set at p < 0.05. For all key performance indicators, 95% confidence intervals (CI) were produced to quantify experimental estimate uncertainty, and the coefficient of variation (CV) was calculated to examine experimental findings' repeatability and consistency.

DATA AVAILABILITY:

The experimental data supporting the findings of this study were generated during the 90-day field evaluation of the proposed IoT-Driven Precision Agriculture (IoT-PA) framework described in the manuscript. The Agriculture Digital Twin Market Report (DataIntelo), used as a background reference for the conceptual development of the framework and to provide context on digital agriculture technologies, is available at: https://dataintelo.com/report/agriculture-digital-twin-market.

Figure 1. Digital Roots: Growing Sustainability in the Agro-Food Chain. Overview of the agro-food value chain illustrating the integration of digital technologies, including IoT, cloud computing, artificial intelligence, and data analytics, to improve agricultural productivity, optimize resource utilization, and support sustainable food production. Please click here to view a larger version of this figure.

Figure 2. Smart Agri-Loop: From Field Sensors to Farmers’ Hands. Workflow of the proposed Internet of Things-Driven Precision Agriculture (IoT-PA) framework showing real-time environmental sensing, wireless data transmission, cloud-based analytics, automated irrigation control, and farmer decision support for precision agriculture. Please click here to view a larger version of this figure.

Figure 3. From Soil to Goal: A Smart Farming Blueprint for Sustainable Growth. Conceptual overview of the proposed IoT-Driven Precision Agriculture (IoT-PA) framework illustrating the integration of digital technologies for smart agricultural management. Please click here to view a larger version of this figure.

Figure 4. From Steam to Smart Farms: The Evolution Toward Agri-Tech Futures. Evolution of agricultural technologies from conventional farming practices to modern digital agriculture through mechanization, precision farming, Internet of Things, IoT-enabled monitoring, cloud computing, and intelligent decision-making systems. Please click here to view a larger version of this figure.

Figure 5. Smart Chains for Safe Grains: A Digital Path to Sustainable Food Futures. Conceptual representation of digital technologies supporting the agricultural supply chain, including crop monitoring, precision irrigation, resource optimization, food quality monitoring, and sustainability assessment to improve food security and environmental performance. Please click here to view a larger version of this figure.

Figure 6. Analysis of water usage. Comparison of water consumption between the conventional irrigation method and the proposed IoT-PA framework. Water consumption was evaluated over the experimental period, and values are presented as mean ± standard deviation (n = 3 independent trials). Statistical significance was assessed using a paired Student's t-test with p < 0.05. The proposed IoT-PA (Internet of Things-Driven Precision Agriculture) framework achieved a 24.62% reduction in water consumption compared with conventional irrigation. Please click here to view a larger version of this figure.

Figure 7. Analysis of crop yield. Comparison of agricultural productivity obtained using the conventional irrigation method and the proposed IoT-PA (Internet of Things-Driven Precision Agriculture) framework under identical cultivation conditions. Crop yield values are reported as mean ± standard deviation (n = 3 independent trials). Statistical significance was evaluated using a paired Student's t-test (p < 0.05). The proposed framework achieved 95.13% agricultural productivity. Please click here to view a larger version of this figure.

Figure 8. Analysis of system efficiency. Performance evaluation of the IoT-PA (Internet of Things-Driven Precision Agriculture) framework based on successful sensing, communication, cloud processing, and automated irrigation operations. Results are expressed as mean ± standard deviation (n = 3 independent trials). Statistical analysis was performed using a paired Student's t-test with p < 0.05. The proposed system achieved an overall system efficiency of 93.85%. Please click here to view a larger version of this figure.

Figure 9. Analysis of Sustainable Resource Optimization. Evaluation of sustainable resource optimization achieved by the proposed IoT-PA framework through efficient water and resource management. Results are presented as mean ± standard deviation (n = 3 independent trials). Statistical significance was determined using a paired Student's t-test (p < 0.05). The proposed framework achieved a 94.25% sustainable resource optimization rate. Please click here to view a larger version of this figure.

Figure 10. Analysis of Digital Technologies in Achieving SDGs. Assessment of the contribution of the proposed IoT-PA (Internet of Things-Driven Precision Agriculture) framework to Sustainable Development Goals (SDGs) through improvements in water-use efficiency, agricultural productivity, intelligent irrigation, and sustainable resource management. Results are presented as mean ± standard deviation (n = 3 independent trials). Statistical significance was evaluated using a paired Student's t-test with p < 0.05. The proposed framework achieved an SDG alignment efficiency of 96.31%. Please click here to view a larger version of this figure.

Discussion

With the IoT-PA, digital agriculture may solve present problems. For resource economies and agricultural production, this paper proposes real-time monitoring, sensor-based irrigation, and data-driven decision-making. Water consumption dropped 24.62%, and agricultural output rose 95.13% using the Internet of Things, demonstrating its revolutionary sustainability potential. SDG 2 (Zero Hunger) and SDG 12 (Responsible Consumption and Production) are met with 93.85% system efficiency. The system achieved 96.31% SDG alignment efficiency. Smart automation replaces resource-intensive alternatives to enhance food security and the environment. The study highlights how sensors, cloud computing, and automation may construct replicable agricultural models. Agriculture needs such technologies because of population growth and climate change. The digital revolution may increase agriculture's efficiency, resilience, and sustainability, according to this essay. The IoT-PA architecture will be applied to crops and regions in future studies. AI will enhance meteorology, predictive analytics, and pest identification. To increase farmer access, emphasis should be placed on low-cost technology and mobile applications. Acceptability, data reception quality, and global sustainability and food security objectives will be defined.

Compared with the Integrated Digital Agriculture & Food Systems Framework (IDAFS) proposed by Sridhar et al.¹⁸, which provides a comprehensive review of digital technologies, including IoT, artificial intelligence (AI), blockchain, robotics, and big data for sustainable agro-food systems, the proposed IoT-PA framework offers a practical implementation for precision agriculture. While IDAFS primarily discusses technology adoption and digital transformation strategies at the conceptual level, IoT-PA integrates real-time environmental sensing, cloud-based data processing, automated irrigation control, and farmer notification into a unified operational framework. Integration allows continuous field monitoring and automated decision-making, making the platform suitable for precision irrigation and resource management¹⁸. Vărzaru's Digital-SDG Impact Analysis Model (DSIAM)¹⁹ emphasizes digital transformation's role in food security and fulfilling the Sustainable Development Goals via policy-level and regional economic analysis. For field implementation, the IoT-PA architecture uses IoT-enabled sensors, automated irrigation control, and cloud communication. Digital transformation is used in agriculture to improve water use and crop production¹⁹. Zhang and Zhang's DVIRF²⁰ promotes sustainable rural development through digital infrastructure, rural industrial integration, and technology innovation. DVIRF supports regional digital transformation without precision irrigation decision-support. To allow smart agriculture, the IoT-PA framework combines continuous sensor monitoring, intelligent irrigation scheduling, cloud-based analytics, and automated resource management²⁰. The proposed IoT-PA architecture combines environmental sensing, connectivity, cloud computing, and automated irrigation for real-time decision-making and water management. Compared to conceptual digital agricultural frameworks^18,19,20, the design enhances operational efficiency, decreases human involvement, and promotes sustainable farming. However, the framework has major drawbacks. This experimental evaluation was done under normal agricultural conditions and has not been confirmed across crop kinds, soil types, climatic regions, or large-scale commercial farming. Predetermined soil moisture thresholds are used in this implementation, which does not leverage AI for predictive irrigation scheduling, crop yield forecasting, pest and disease detection, or digital twin-based crop simulation. Future research will use machine learning, digital twins, remote sensing, and explainable AI to enhance agricultural prediction, scalability, and flexibility.

Limitations must be considered when interpreting IoT-Driven Precision Agriculture (IoT-PA) results. In general, the framework has not been tested across crop types, soil characteristics, climatic circumstances, or large-scale farming contexts. For optimal performance under varied cultivation practices, irrigation management employs soil moisture thresholds that may necessitate crop-specific calibration. This application leverages IoT-based environmental monitoring and automated irrigation management, not AI-driven predictive irrigation, pest and disease diagnosis, nutrient management, or multispectral remote sensing. Network connectivity, sensor calibration accuracy, and climatic factors affecting real-time data transmission may impair framework performance in remote agricultural areas.

Materials

List of materials used in this article

Name	Company	Catalog Number	Comments
Arduino IDE	Arduino	Version 2.x https://www.arduino.cc/en/software	Integrated Development Environment, ESP32 firmware development
Capacitive Soil Moisture Sensor	DFRobot	SEN0193	Measures volumetric soil moisture; Operating voltage 3.3–5.5 V
Cloud IoT Platform	Amazon Web Services	AWS IoT Core https://aws.amazon.com/iot-core	Cloud-based IoT platform for data storage, visualization, and remote monitoring
DC Power Supply	Mean Well	/	Supplies power to controller and pump; 12 V DC regulated output, Model: LRS-50-12
DC Water Pump	Commercially available	/	Automated irrigation; 12 V DC Pump
Digital Light Intensity Sensor	Rohm Semiconductor	BH1750FVI	Measures ambient light intensity; 1–65535 lux
ESP32 Development Board	Espressif Systems	ESP32-DEVKITC-32D	Dual-core 240 MHz MCU, Wi-Fi/Bluetooth; Main controller for sensor acquisition and irrigation control
Microsoft Excel	Microsoft Corporation	Microsoft 365 https://www.microsoft.com/microsoft-365/excel	Spreadsheet software for data organization and visualization
MQTT Broker	Eclipse Foundation	Mosquitto v2.x https://mosquitto.org	IoT message communication; MQTT protocol
Python	Python Software Foundation	Version 3.x https://www.python.org	Programming language for data preprocessing and statistical analysis
Rainfall Sensor Module	DFRobot	/	Analog/Digital output; Detects rainfall events; Model: SEN0308
Single-Channel Relay Module	Songle	SRD-05VDC-SL-C	Switches irrigation pump ON/OFF; 5 V relay
Temperature and Humidity Sensor	Adafruit Industries	DHT22 (AM2302)	Environmental monitoring; Temperature ±0.5 °C; Humidity ±2% RH
Web Browser	Google LLC	Google Chrome (latest stable release) https://www.google.com/chrome	Access to AWS IoT dashboard
Wi-Fi Router	TP-Link Technologies	/	Wireless communication between ESP32 and cloud; IEEE 802.11 b/g/n/ac; Model: Archer C6