Prediction of carbon dioxide (CO2) emissions from agricultural soil is vital for efficient and strategic mitigating practices and achieving climate smart agriculture. This study aimed to evaluate the ability of two machine learning algorithms [gradient boosting regression (GBR), support vector regression (SVR)], and two deep learning algorithms [feedforward neural network (FNN) and convolutional neural network (CNN)] in predicting CO2 emissions from Maize fields in two agroclimatic regions i.e., continental (Debrecen-Hungary), and semi-arid (Karaj-Iran). This research developed three scenarios for predicting CO2. Each scenario is developed by a combination between input variables [i.e., soil temperature (Δ), soil moisture (θ), date of measurement (SD), soil management (SM)] [i.e., SC1: (SM + Δ + θ), SC2: (SM + Δ), SC3: (SM + θ)]. Results showed that the average CO2 emission from Debrecen was 138.78 ± 72.04 ppm (n = 36), while the average from Karaj was 478.98 ± 174.22 ppm (n = 36). Performance evaluation results of train set revealed that high prediction accuracy is achieved by GBR in SC1 with the highest R² = 0.8778, and lowest root mean squared error (RMSE) = 72.05, followed by GBR in SC3. Overall, the performance MDLM is ranked as GBR > FNN > CNN > SVR. In testing phase, the highest prediction accuracy was achieved by FNN in SC1 with R² = 0.918, and RMSE = 67.75, followed by FNN in SC3, and GBR in SC1 (R² = 0.887, RMSE = 79.881). The performance of MDLM ranked as FNN > GRB > CNN > SVR. The findings of the research provide insights into agricultural management strategies, enabling stakeholders to work towards a more sustainable and climate-resilient future in agriculture.

This study presents a LoRaWAN-based IoT system developed for real-time monitoring of ammonia (NH₃) emissions in cereal crop fields. Sustainable agriculture increasingly demands on-farm greenhouse gas (GHG) tracking linked to environmental variables. IoT offers efficient real-time monitoring of soil NH₃ emissions and associated factors. Our research introduces a unique Field Monitoring Laboratory: a LoRaWAN-connected IoT system integrating soil, crop, and microclimate sensors to observe NH₃⁺, air temperature, rainfall, humidity, soil temperature, and moisture content. The system comprises a field lab, data server, and custom dashboard with analytics capabilities. NH₃ fluxes were measured in autumn-sown cereals across three growing seasons (2020–2023). Tukey’s Kramer test revealed significant (p < 0.05, p < 0.001) differences in NH₃ emissions and environmental variables between years. Highest NH₃ emissions (1.94 ppm in 2020, 1.71 ppm in 2021) coincided with elevated air (25–31 °C) and soil (21–23 °C) temperatures, and higher mean and peak rainfall (0.40–0.48 mm average; max 9–31.6 mm). Principal Component Analysis showed 65.8% variance explained by PC1 and PC2, with high loadings from temperature and soil moisture. Spearman’s correlation indicated moderate positive associations (r = 0.38–0.4, p < 0.05) of NH₃ with soil moisture at 20 cm and 40 cm of soil depth, and a weak negative correlation (r = -0.16 and − 0.17) with soil temperature at 20 cm and 40 cm. The study underscores the potential of IoT technology using calibrated gas sensors and LoRaWAN for real-time NH₃ and environmental monitoring, enabling informed decision-making in smart agriculture.