Applying the IoT paradigm in agriculture generates an unprecedented amount of data about fields and crops worldwide. With data, machine learning is natural to forecast or estimate crop parameters, which is remarkable for the estimation of evapotranspiration and soil moisture to propose irrigation plans and control, among other applications. This work investigates the literature to evaluate what kind of IoT devices and machine learning algorithms are being applied in precision agriculture and discusses the effectiveness of such equipment and algorithms on different spatial scales. The results indicate IoT devices are commonly applied in small crop areas or greenhouses and for short periods of time, usually less than one growing season. Machine learning models are also applied in similar scenarios, and the effectiveness of such techniques is discussed according to growers' needs and ambitions.

Irrigation automation and Internet of Things (IoT) smart sensing improve water management and reduce labor in broadacre farming. This work investigates the feasibility of an innovative Wireless Fidelity (Wi-Fi) wireless mesh sensor network (WMSN) architecture to provide large-scale coverage (up to ~900 ha) and assesses its performance against the influence of crop canopy development. The study, conducted on two commercial rice farms, demonstrated the WMSN’s effectiveness in providing stable coverage with 98.89% message success after one retransmission. The network maintained a signal strength (RSSI) above the −85 dBm operational threshold within 800 m of a communication pod, with a stable mesh link established between pods up to 853 m apart. Results showed a strong negative linear correlation between rice canopy height and RSSI, with attenuation indices ranging from 2.34 to 2.88. Positioning the equipment 1.5 m above the canopy effectively mitigated the attenuation, achieving near free-space conditions.

Detecting soil–water conditions ranging from dry to fully ponded in rice fields using solely multispectral remote sensing is crucial for irrigation water management practices focused on water savings in Semi-Arid Australia. To this end, this research employed the Minimum Redundancy Maximum Relevance (mRMR) algorithm to identify a set of multispectral remote sensing indices for use with Machine Learning (ML) to predict three soil–water conditions in irrigated rice: “Flooded”, “Saturated”, and “Dry”. Two models were developed: Model 1, using the most frequently used remote sensing indices in the literature; Model 2, including multispectral variables selected by the mRMR algorithm. Model 2 achieved the highest performance, with an accuracy of 0.64 and a $\mathrm{k}\mathrm{a}\mathrm{p}\mathrm{p}\mathrm{a}$ of 0.46, and ROC-AUC values of 0.87, 0.62, and 0.83 for “Flooded”, “Saturated”, and “Dry”, respectively. All models exhibit high confusion rates between “Flooded” and “Saturated” conditions, suggesting that multispectral remote sensing doesn’t provide sufficient information to distinguish these soil–water conditions. The SHAP analysis revealed that vegetation-sensitive indices encoding information on crop biomass, plant moisture, and senescence status were the primary drivers of soil–water condition prediction.

Water is crucial for rice growth, particularly in semi-arid Australia, where climate change threatens water allocation for rice growers and challenges the sustainability of the rice industry. Estimating water depth using remote sensing can be beneficial, as it can help growers transition from traditional continuous flooding (CF) to irrigation practices such as Delayed Permanent Water (DPW) and Aerobic Rice (AR), which are promising pathways to ensure industry sustainability. Synthetic aperture radar (SAR) has been widely evaluated for water depth prediction in rice crops. To date, a significant gap remains in the performance of the proposed models, with authors suggesting the use of optical and SAR data to improve their estimates. To this end, this research evaluated three machine learning (ML) models to estimate water depth in rice under different irrigation practices in the Australian semi-arid region. Three different ML approaches (Tree-based, Neural Networks, and pretrained foundational model) were evaluated with three data configurations: Set 1 with SAR only, set 2 with Optical Only, and Set 3 with multimodal (SAR and Optical) data. The pre-trained foundational model achieved the best results, with RMSE of 14.19 cm, MAE of 10.01 cm, R² of 0.63, KGE of 0.73, and CCC of 0.78. Interestingly, the SHAP analysis reveals that optical remote sensing is more significant for the model than SAR. Specifically, the mean GVMI and VAWI_log standard deviation.

Rice (Oryza sativa) is a high water-demand crop, with yield strongly dependent on irrigation water availability, particularly in the semi-arid Riverina region of Australia. Enhancing the drought resilience of rice production therefore requires improved water management strategies, such as Aerobic Rice (AR) as an alternative to the traditional Continuous Flooding (CF) strategy. To better characterize AR water-saving potential, the main components of the water balance were measured under these systems. Net irrigation was measured using the Agriflo XCi ultrasonic Doppler sensor, and evapotranspiration (ET) with the LI-710 Eddy Covariance sensor. Three commercial-scale rice farms during the 2024–2025 season in the Riverina region were monitored. The analysis focused on three aspects: (i) rice crop development, (ii) water management and water balance, and (iii) rice performance and water productivity indicators. Water savings associated with AR were estimated at 18.4% in a side-by-side comparison. In addition, final harvested yield increased by 5.5%, resulting in a 29.5% increase in water productivity. ET from the AR paddock was 6.5% higher than under CF. Nevertheless, AR reduced Deep Percolation (DP) by 59.0% compared with CF. Two other CF paddocks were also monitored across the region, and water use from 13.0 to 14.5 ML ha^-1 has been observed as the baseline irrigation water requirement for permanent ponded rice paddocks in this region. These findings provide evidence that AR can deliver meaningful water savings while improving water productivity in commercial-scale rice paddocks in this semi-arid region of Riverina.