Mid-season nitrogen (N) application in rice crops can maximize yield and profitability. This requires accurate and efficient methods of determining rice N uptake in order to prescribe optimal N amounts for topdressing. This study aims to determine the accuracy of using remotely sensed multispectral data from satellites to predict N uptake of rice at the panicle initiation (PI) growth stage, with a view to providing optimum variable-rate N topdressing prescriptions without needing physical sampling. Field experiments over 4 years, 4–6 N rates, 4 varieties and 2 sites were conducted, with at least 3 replicates of each plot. One WorldView satellite image for each year was acquired, close to the date of PI. Numerous single- and multi-variable models were investigated. Among single-variable models, the square of the NDRE vegetation index was shown to be a good predictor of N uptake (R² = 0.75, RMSE = 22.8 kg/ha for data pooled from all years and experiments). For multi-variable models, Lasso regularization was used to ensure an interpretable and compact model was chosen and to avoid over fitting. Combinations of remotely sensed reflectances and spectral indexes as well as variety, climate and management data as input variables for model training achieved R² < 0.9 and RMSE < 15 kg/ha for the pooled data set. The ability of remotely sensed data to predict N uptake in new seasons where no physical sample data has yet been obtained was tested. A methodology to extract models that generalize well to new seasons was developed, avoiding model overfitting. Lasso regularization selected four or less input variables, and yielded R² of better than 0.67 and RMSE better than 27.4 kg/ha over four test seasons that weren’t used to train the models.

WiFi is starting to be adopted in agricultural settings because of the increasing use of data-centric farming devices and applications. Some of these applications require high data rates that other radio standards cannot offer, for example, realtime yield mapping, drone-based image upload and viewing and video monitoring. It is therefore desirable for farming wireless sensor networks (WSNs) to also utilise available on-farm WiFi networks. However, little information is available on WiFi signal propagation in these environments, as agricultural WSNs have traditionally been based on other radio standards. Therefore, the 2.4GHz WiFi signal propagation characteristics in real outdoor agricultural cropping environments were investigated using infield data loggers. Three distinct farming environments were studied, (i) bare fields, (ii) cotton fields, and (iii) ponded-water rice fields. We studied the effects of (i) weather conditions, (ii) crop growth and (iii) water depth on signal strength across an entire growing season. We also studied the range of reliable data transfer in each environment as a function of height of the logger WiFi antenna above the crop. Crop growth status was found to be much more significant in determining signal strength than weather conditions, with signal strength declining by 8dB over the season in a cotton field, and by 20dB in a rice field. In rice and cotton crops, provided the radios remain 20cm above the crop canopy, ranges in excess of 1km were measured. Significantly greater ranges are predicted if the antenna is more than 40cm above the top of the crop. Regression models were fitted to the measurements to allow predictions and recommendations, with correlation coefficient of determination (R2) values of better than 0.9 in most cases. Radio path loss exponents depended on the environment, and were typically between 3 and 5.

Multisensor capacitance probes (MCPs) have traditionally been used for soil moisture monitoring and irrigation scheduling. This paper presents a new application of these probes, namely the simultaneous monitoring of ponded water level, soil moisture, and temperature profile, conditions which are particularly important for rice crops in temperate growing regions and for rice grown with prolonged periods of drying. WiFi-based loggers are used to concurrently collect the data from the MCPs and ultrasonic distance sensors (giving an independent reading of water depth). Models are fit to MCP water depth vs volumetric water content (VWC) characteristics from laboratory measurements, variability from probe-to-probe is assessed, and the methodology is verified using measurements from a rice field throughout a growing season. The root-mean-squared error of the water depth calculated from MCP VWC over the rice growing season was 6.6 mm. MCPs are used to simultaneously monitor ponded water depth, soil moisture content when ponded water is drained, and temperatures in root, water, crop and ambient zones. The insulation effect of ponded water against cold-temperature effects is demonstrated with low and high water levels. The developed approach offers advantages in gaining the full soil-plant-atmosphere continuum in a single robust sensor.

Previous studies have shown the utility of remotely-sensed multispectral imagery and vegetation indices derived from the imagery (such as Normalised Differential Vegetation Index - NDVI) for monitoring of peanut growth status. Applications include assessing within- and between-paddock biomass variability and predicting yield. This data is useful for growers managing in-field variability, and for processors managing operational logistics and financial forecasting. However, peanuts grown in Australia, and globally, are grown in areas where there is frequent cloud cover. This limits the applicability of satellite-based multispectral imagery for operational monitoring as the chance of a cloud-free capture on a required date are low. In contrast to multispectral imagery, synthetic-aperture radar (SAR) imagery is not limited by cloud cover. This paper assesses multiple uses of SAR imagery for peanut operations. A time-series of freely-available Sentinel-1 SAR images for the 2018-2019 season was obtained for this purpose, covering more than 50 peanut fields in the Bundaberg coastal cropping region located in south-eastern Queensland. The radar imagery was highly correlated with the limited cloud-free multispectral imagery from the Sentinel-2 platform over the same time period, with a significant correlation between multispectral NDVI and combinations of radar bands on multiple dates (r= 0.87) observed. Time-series growth profiles from the SAR data were also derived and assessment was made of their ability to estimate the crop emergence characteristics, actual harvest dates, and prediction of pod yield. Our results highlight the possibility for SAR data being used to replace multispectral data when the latter has limited availability due to presence of cloud cover on target peanut fields.

A new agricultural sensor data logging platform (WiField) is described, based on IEEE 802.11 WiFi technology. It is low-cost, low-power, and achieves long (>2km) range communication to on-farm WiFi access points. WiFi is an attractive choice for this application because of the wide range of other devices that increasingly need internet access in farming systems. The WiField devices include interfaces for many sensor types; weather, infrastructure (tank and irrigation water levels), and soil status sensing. The interfaces and example corresponding sensors include SDI-12 (capacitive soil moisture probes), soil tension (matric potential), analog voltage and current, UART (water depth sensing using ultrasonic transducers with a digital interface), RS-422 (integrated weather stations), one-wire (DS18B20 temperature sensors) and pulse (flow meters, wind and rain sensors). It integrates solar charging of rechargeable batteries, or can be run off disposable batteries for at least an entire growing season due to design choices that minimize power consumption. It is designed to upload data to cloud services in real-time. The data is then processed in the cloud and interactive graphs are produced, so multiple users can access up-to-date information in order to make optimized, timely farming decisions. The use of the WiField devices in a cotton farming operation is described, for scheduling irrigations and determining crop water use through the soil profile.

The main objective of this work was to study the feasibility of using the green red vegetation index (GRVI) and the red edge ratio (RE/R) obtained from UAS imagery for monitoring the effects of soil water deficit and for predicting fibre quality in a surface-irrigated cotton crop. The performance of these indices to track the effects of water stress on cotton was compared to that of the normalised difference vegetation index (NDVI) and crop water stress index (CWSI). The study was conducted during two consecutive seasons on a commercial farm where three irrigation frequencies and two nitrogen rates were being tested. High-resolution multispectral images of the site were acquired on four dates in 2017 and six dates in 2018, encompassing a range of matric potential values. Leaf stomatal conductance was also measured at the image acquisition times. At harvest, lint yield and fibre quality (micronaire) were determined for each treatment. Results showed that within each year, the N rates tested (> 180 kg N ha⁻¹) did not have a statistically significant effect on the spectral indices. Larger intervals between irrigations in the less frequently irrigated treatments led to an increase (p < 0.05) in the CWSI and a reduction (p < 0.05) in the GRVI, RE/R, and to a lesser extent in the NDVI. A statistically significant and good correlation was observed between the GRVI and RE/R with soil matric potential and stomatal conductance at specific dates. The GRVI and RE/R were in accordance with the soil and plant water status when plants experienced a mild level of water stress. In most of the cases, the GRVI and RE/R displayed long-term effects of the water stress on plants, thus hampering their use for determinations of the actual soil and plant water status. The NDVI was a better predictor of lint yield than the GRVI and RE/R. However, both GRVI and RE/R correlated well (p < 0.01) with micronaire in both years of study and were better predictors of micronaire than the NDVI. This research presents the GRVI and RE/R as good predictors of fibre quality with potential to be used from satellite platforms. This would provide cotton producers the possibility of designing specific harvesting plans in the case that large fibre quality variability was expected to avoid discount prices. Further research is needed to evaluate the capability of these indices obtained from satellite platforms and to study whether these results obtained for cotton can be extrapolated to other crops.

The present work assessed the usefulness of a set of spectral indices obtained from an unmanned aerial system (UAS) for tracking spatial and temporal variability of nitrogen (N) status as well as for predicting lint yield in a commercial cotton (Gossypium hirsutum L.) farm. Organic, inorganic and a combination of both types of fertilizers were used to provide a range of eight N rates from 0 to 340 kg N ha⁻¹. Multi-spectral images (reflectance in the blue, green, red, red edge and near infrared bands) were acquired on seven days throughout the season, from 62 to 169 days after sowing (DAS), and data were used to compute structure- and chlorophyll-sensitive vegetation indices (VIs). Above-ground plant biomass was sampled at first flower, first cracked boll and maturity and total plant N concentration (N%) and N uptake determined. Lint yield was determined at harvest and the relationships with the VIs explored. Results showed that differences in plant N% and N uptake between treatments increased as the season progressed. Early in the season, when fertilizer applications can still have an effect on lint yield, the simplified canopy chlorophyll content index (SCCCI) was the index that best explained the variation in N uptake and plant N% between treatments. Around first cracked boll and maturity, the linear regression obtained for the relationships between the VIs and both plant N% and N uptake was statistically significant, with the highest r² values obtained at maturity. The normalized difference red edge (NDRE) index, and SCCCI were generally the indices that best distinguished the treatments according to the N uptake and total plant N%. Treatments with the highest N rates (from 307 to 340 kg N ha⁻¹) had lower normalized difference vegetation index (NDVI) than treatments with 0 and 130 kg N ha⁻¹ at the first measurement day (62 DAS), suggesting that factors other than fertilization N rate affected plant growth at this early stage of the crop. This fact affected the earliest date at which the structure-sensitive indices NDVI and the visible atmospherically resistant index (VARI) enabled yield prediction (97 DAS). A statistically significant linear regression was obtained for the relationships between SCCCI and NDRE with lint yield at 83 DAS. Overall, this study shows the practicality of using an UAS to monitor the spatial and temporal variability of cotton N status in commercial farms. It also illustrates the challenges of using multi-spectral information for fertilization recommendation in cotton at early stages of the crop.

This study integrates measured soil moisture sensor data, a remotely sensed crop vegetation index, and weather data to train models, in order to predict future soil moisture. The study was carried out on a cotton farm, with wireless soil moisture monitoring equipment deployed across five plots. Lasso, Decision Tree, Random Forest and Support Vector Machine modeling methods were trialled. Random Forest models gave consistently good results (mean 7-day prediction error from 8.0 to 16.9 kPA except in one plot with malfunctioning sensors). Linear regression with two of the most important predictor variables was not as accurate, but allowed extraction of an interpretable model. The system was implemented in Google Cloud Platform and a model was trained continuously through the season. An online irrigation dashboard was created showing previous and forecast soil moisture conditions, along with weather and normalized difference vegetation index (NDVI). This was used to guide operators in advance of irrigation water needs. The methodology developed in this study could be used as part of a closed-loop sensing and irrigation automation system.

Irrigated agriculture requires high reliability from water delivery networks and high flows to satisfy demand at seasonal peak times. Aquatic vegetation in irrigation channels are a major impediment to this, constraining flow rates. This work investigates the use of remote sensing from unmanned aerial vehicles (UAVs) and satellite platforms to monitor and classify vegetation, with a view to using this data to implement targeted weed control strategies and assessing the effectiveness of these control strategies. The images are processed in Google Earth Engine (GEE), including co-registration, atmospheric correction, band statistic calculation, clustering and classification. A combination of unsupervised and supervised classification methods is used to allow semi-automatic training of a new classifier for each new image, improving robustness and efficiency. The accuracy of classification algorithms with various band combinations and spatial resolutions is investigated. With three classes (water, land and weed), good accuracy (typical validation kappa >0.9) was achieved with classification and regression tree (CART) classifier; red, green, blue and near-infrared (RGBN) bands; and resolutions better than 1 m. A demonstration of using a time-series of UAV images over a number of irrigation channel stretches to monitor weed areas after application of mechanical and chemical control is given. The classification method is also applied to high-resolution satellite images, demonstrating scalability of developed techniques to detect weed areas across very large irrigation networks.