Sensing technologies for precision specialty crop production

With the advances in electronic and information technologies, various sensing systems have been developed for specialty crop production around the world. Accurate information concerning the spatial variability within fields is very important for precision farming of specialty crops. However, this variability is affected by a variety of factors, including crop yield, soil properties and nutrients, crop nutrients, crop canopy volume and biomass, water content, and pest conditions (disease, weeds, and insects). These factors can be measured using diverse types of sensors and instruments such as field-based electronic sensors, spectroradiometers, machine vision, airborne multispectral and hyperspectral remote sensing, satellite imagery, thermal imaging, RFID, and machine olfaction system, among others. Sensing techniques for crop biomass detection, weed detection, soil properties and nutrients are most advanced and can provide the data required for site specific management. On the other hand, sensing techniques for diseases detection and characterization, as well as crop water status, are based on more complex interaction between plant and sensor, making them more difficult to implement in the field scale and more complex to interpret. This paper presents a review of these sensing technologies and discusses how they are used for precision agriculture and crop management, especially for specialty crops. Some of the challenges and considerations on the use of these sensors and technologies for specialty crop production are also discussed.     

Interdisciplinary Irrigated Precision Farming Research

The USDA-Agricultural Research Service and Colorado State University are conducting an interdisciplinary study that focuses on developing a clearer scientific understanding of the causes of yield variability. Two years of data have been collected from two commercial center pivot irrigated fields (72 and 52 ha). Cooperating farmers manage all farming operations for crop production and provide yield maps of the maize grown on the fields. The farmers apply sufficient inputs to minimize risk of yield loss. The important variables for crop production have been sampled at a grid spacing of 76 m for two seasons. A spatial auto-regressive model was fitted to the data to determine the critical factors affecting yield variability. Thirty one layers of data were included in the analysis, and a total of over 140,000 models were examined. Up to five predictors were used in each model. Variability in water application, nitrate nitrogen, organic matter, phosphorus, topology, percent silt and soil electrical conductivity were significant in explaining the yield variability for Field 1. Variability in water application, ammonium, nematodes, percent clay, insects, potassium, soil electrical conductivity, and topology were significant in explaining the yield variability for Field 2. The tentative conclusion is that the potential economic benefit of site specific management is small where the farmer's management tolerance for risk is low. The potential of site specific management is in reducing the cost of inputs and environmental impact, but could increase risk.     

Quantifying spatial variability of indigenous nitrogen supply for precision nitrogen management in small scale farming

Understanding spatial variability of indigenous nitrogen (N) supply (INS) is important to the implementation of precision N management (PNM) strategies in small scale agricultural fields of the North China Plain (NCP). This study was conducted to determine: (1) field-to-field and within-field variability in INS; (2) the potential savings in N fertilizers using PNM technologies; and (3) winter wheat (Triticum aestivum L.) N status variability at the Feekes 6 stage and the potential of using a chlorophyll meter (CM) and a GreenSeeker active crop canopy sensor for estimating in-season N requirements. Seven farmer’s fields in Quzhou County of Hebei Province were selected for this study, but no fertilizers were applied to these fields. The results indicated that INS varied significantly both within individual fields and across different fields, ranging from 33.4 to 268.4 kg ha⁻¹, with an average of 142.6 kg ha⁻¹ and a CV of 34%. The spatial dependence of INS, however, was not strong. Site-specific optimum N rates varied from 0 to 355 kg ha⁻¹ across the seven fields, with an average of 173 kg ha⁻¹ and a CV of 46%. Field-specific N management could save an average of 128 kg N ha⁻¹ compared to typical farmer practices. Both CM and GreenSeeker sensor readings were significantly related to crop N status and demand across different farmer’s fields, showing a good potential for in-season site-specific N management in small scale farming systems. More studies are needed to further evaluate these sensing technology-based PNM strategies in additional farmer fields in the NCP.     

Integrating remote sensing information with crop model to monitor wheat growth and yield based on simulation zone partitioning

Research into crop growth models at the spatial scale is of great significance for evaluating crop growth, predicting grain yield and studying global climate change. Coupling spatial remote sensing (RS) data can effectively promote the simulation of growth models at spatial scales. However, the integration of RS data and crop models to produce a coupled model based on pixel by pixel requires a large amount of calculations. Simulation zone partitioning is used to separate and cluster the large area into a few relatively uniform zones. Then, the growth model can run on the basis of these units. This method both reflects spatial heterogeneity and avoids repeated simulations of regions with similar attributes, improving the simulation efficiency. In this study, simulation partitioning was performed using soil nutrient indices (organic matter content, total nitrogen content and available potassium content) and corresponding spatial characteristics of wheat growth, as indicated by RS data. A coupled model, integrating RS information and the WheatGrow model, using vegetation indices as the coupling parameters (based on the Particle Swarm Optimization algorithm and PROSAIL model), was developed. The aim was to realize accurate prediction of wheat growth parameters and grain yield at the spatial scale. Good zone partitions were obtained by partitioning with the spatial combination of soil nutrient indices and the wheat canopy vegetation index, calculated during the main growth (jointing, heading and filling) stages. The variation coefficients of each index within individual simulation sub-zones were much smaller than those of the indices across the whole area. An analysis of variance showed that the indices were significantly different between the simulation sub-zones, which indicated that appropriate simulated sub-zones had been defined. The minimum root mean square error of the leaf area index, leaf nitrogen accumulation and yield between the predicted values and the values simulated by the coupled model were 0.92, 1.12 g m^?2, and 409.70 kg ha^?1, respectively, which were obtained when the soil-adjusted vegetation index was used as a partitioning zone and assimilating parameter. These results demonstrated that the coupled model of the crop model and RS data, based on the simulation sub-zones had a good prediction accuracy. The results provide important technical support for increasing model efficiency, when crop models need to be applied at the spatial scale.     

Comparison of QuickBird Satellite Imagery and Airborne Imagery for Mapping Grain Sorghum Yield Patterns

Timely and accurate information on crop conditions obtained during the growing season is of vital importance for crop management. High spatial resolution satellite imagery has the potential for mapping crop growth variability and identifying problem areas within fields. The objectives of this study were to use QuickBird satellite imagery for mapping plant growth and yield patterns within grain sorghum fields as compared with airborne multispectral image data. A QuickBird 2.8-m four-band image covering a cropping area in south Texas, USA was acquired in the 2003 growing season. Airborne three-band imagery with submeter resolution was also collected from two grain sorghum fields within the satellite scene. Yield monitor data collected from the two fields were resampled to match the resolutions of the airborne imagery and the satellite imagery. The airborne imagery was related to yield at original submeter, 2.8 and 8.4 m resolutions and the QuickBird imagery was related to yield at 2.8 and 8.4 m resolutions. The extracted QuickBird images for the two fields were then classified into multiple zones using unsupervised classification and mean yields among the zones were compared. Results showed that grain yield was significantly related to both types of image data and that the QuickBird imagery had similar correlations with grain yield as compared with the airborne imagery at the 2.8 and 8.4 m resolutions. Moreover, the unsupervised classification maps effectively differentiated grain production levels among the zones. These results indicate that high spatial resolution satellite imagery can be a useful data source for determining plant growth and yield patterns for within-field crop management.     

Underlying causes of yield spatial variability and potential for precision management in rice systems

Our current understanding of the mechanisms driving spatiotemporal yield variability in rice systems is insufficient for effective management at the sub-field scale. The overall objective of this study was to evaluate the potential of precision management for rice production. The spatiotemporal properties of multiyear yield monitor data from four rice fields, representing varying soil types and locations within the primary rice growing region in California, were quantified and characterized. The role of water management, land-leveling, and the spatial distribution of soil properties in driving yield heterogeneity was explored. Mean yield and coefficient of variation at the sampling points within each field ranged from 9.2 to 12.1 Mg ha^?1 and from 7.1 to 14.5 %, respectively. Using a k-means clustering and randomization method, temporally stable yield patterns were identified in three of the four fields. Redistribution of dissolved organic carbon, nitrogen, potassium and salts by lateral flood water movement was observed across all fields, but was only related to yield variability via exacerbating areas with high soil salinity. The effects of cold water temperature and land-leveling on yield variability were not observed. Soil electrical conductivity and/or plant available phosphorus were identified as the underlying causes of the within-field yield patterns using classification and regression trees. Our results demonstrate that while the high temporal yield variability in some rice fields does not permit precision management, in other fields exhibiting stable yield patterns with identifiable causes, precision management and modified water management may improve the profitability and resource-use efficiency of rice production systems.     

Estimation of soil organic carbon stock and its controlling factors in cropland of Yunnan Province,China

Soil organic carbon(SOC) is the most important indicators of soil quality and health.Identifying the spatial distribution of SOC and its influencing factors in cropland is crucial to understand the terrestrial carbon cycle and optimize agronomic management.Yunnan Province,characterized by mountainous topography and varied elevation,is one of the highest SOC regions in China.Yet its SOC stock of cropland and influencing factors has not been fully studied due to the lack of adequate soil investiga...     

Application of artificial neural networks in yield prediction of potato crop

Forecasting of crop yield is helpful in food management and growth of a nation, which has specially agriculture based economy. In the last few decades, Artificial Neural Networks have been used successfully in different fields of agricultural remote sensing especially in crop type classification and crop area estimation. The present work employed two types of Artificial Neural Networks i.e., a Generalized Regression Neural Network (GRNN) and a Radial Basis Function Neural Network (RBFNN) to predict the yield of potato crops, which have been sown differently (flat and rough). Crop parameters like leaf area index, biomass and plant height were used as input data, while the yield of potato fields as output dataset to train and test the Neural Networks. Both GRNN and RBNN predicted potato crop yield accurately. However based on quick learning capability and lower spread constant (0.5), the GRNN was found a better predictor than RBFNN. Furthermore, the rough surface field was found more productive than flat field.     

Crop water stress mapping for site-specific irrigation by thermal imagery and artificial reference surfaces

Variable-rate irrigation by machines or solid set systems has become technically feasible, however mapping crop water status is necessary to match irrigation quantities to site-specific crop water demands. Remote thermal sensing can provide such maps in sufficient detail and in a timely way. In a set of aerial and ground scans at the Hula Valley, Israel, digital crop water stress maps were generated using geo-referenced high-resolution thermal imagery and artificial reference surfaces. Canopy-related pixels were separated from those of the soil by upper and lower thresholds related to air temperature, and canopy temperatures were calculated from the coldest 33% of the pixel histogram. Artificial surfaces that had been wetted provided reference temperatures for the crop water stress index (CWSI) normalized to ambient conditions. Leaf water potentials of cotton were related linearly to CWSI values with R ² = 0.816. Maps of crop stress level generated from aerial scans of cotton, process tomatoes and peanut fields corresponded well with both ground-based observations by the farm operators and irrigation history. Numeric quantification of stress levels was provided to support decisions to divide fields into sections for spatially variable irrigation scheduling.     

Modelling Wild-Oat Density in Terms of Soil Factors: A Machine Learning Approach

In crop fields, weed density varies spatially in non-random patterns. Initial knowledge of weed distribution would greatly improve weed management for Precision Agriculture operations. Site properties could be correlated to weed distribution, since the former vary among crop fields and also certain factors such as soil texture or nitrogen may condition the weed growth. This paper presents a method, based on artificial intelligence techniques, for inducing a model that appropriately predicts the heterogeneous distribution of wild-oat (Avena sterilis L.) in terms of some environmental variables. From several experiments, distinct rule sets have been found by applying a genetic algorithm to carry out the automatic learning process. The best rule set extracted was able to explain about 88% of weed variability.     

小麦栽培管理知识模型系统的设计与实现

在总结、归纳和提炼小麦栽培理论与技术的研究成果和知识积累的基础上，运用系统学方法和结构化途径，建立了具有时空适应性的小麦栽培管理动态知识模型系统，用于确定不同环境条件和生产系统下的小麦生育特征及栽培管理技术方案，系统包括：产量水平与产量结构、主要品质指标、品种类型、播种期、基本苗、播种量、适宜生育期；主要生育期的茎蘖数、叶龄、叶面积指数、生物量等动态指标；有效叶面积率、高效叶面积率和粒叶比等源库指标；氮、磷、钾肥料运筹及主要生育期的水分管理等。本系统克服了传统作物栽培模式与专家系统的地域性强和广适性差的不足，从而为实现作物栽培管理的定量化和信息化奠定了基础。     

Airborne Hyperspectral Imagery and Yield Monitor Data for Mapping Cotton Yield Variability

Increased availability of hyperspectral imagery necessitates the evaluation of its potential for precision agriculture applications. This study examined airborne hyperspectral imagery for mapping cotton (Gossypium hirsutum L.) yield variability as compared with yield monitor data. Hyperspectral images were acquired using an airborne imaging system from two cotton fields during the 2001 growing season, and yield data were collected from the fields using a cotton yield monitor. The raw hyperspectral images contained 128 bands between 457 and 922 nm. The raw images were geometrically corrected, georeferenced and resampled to 1 m resolution, and then converted to reflectance. Aggregation functions were then applied to each of the 128 bands to reduce the cell resolution to 4 m (close to the cotton picker's cutting width) and 8 m. The yield data were also aggregated to the two grids. Correlation analysis showed that cotton yield was significantly related to the image data for all the bands except for a few bands in the transitional range from the red to the near-infrared region. Stepwise regression performed on the yield and hyperspectral data identified significant bands and band combinations for estimating yield variability for the two fields. Narrow band normalized difference vegetation indices derived from the significant bands provided better yield estimation than most of the individual bands. The stepwise regression models based on the significant narrow bands explained 61% and 69% of the variability in yield for the two fields, respectively. To demonstrate if narrow bands may be better for yield estimation than broad bands, the hyperspectral bands were aggregated into Landsat-7 ETM+ sensor's bandwidths. The stepwise regression models based on the four broad bands explained only 42% and 58% of the yield variability for the two fields, respectively. These results indicate that hyperspectral imagery may be a useful data source for mapping crop yield variability.     

The delineation of agricultural management zones with high resolution remotely sensed data

Remote sensing (RS) techniques have been widely considered to be a promising source of information for land management decisions. The objective of this study was to develop and compare different methods of delineating management zones (MZs) in a field of winter wheat. Soil and yield samples were collected, and five main crop nutrients were analyzed: total nitrogen (TN), nitrate nitrogen (NN), available phosphorus (AP), extractable potassium (EP) and organic matter (OM). At the wheat heading stage, a scene of Quickbird imagery was acquired and processed, and the optimized soil-adjusted vegetation index (OSAVI) was determined. A fuzzy k-means clustering algorithm was used to define MZs, along with fuzzy performance index (FPI), and modified partition entropy (MPE) for determining the optimal number of clusters. The results showed that the optimal number of MZs for the present study area was three. The MZs were delineated in three ways; based on soil and yield data, crop RS information and the combination of soil, yield and RS information. The evaluation of each set of MZs showed that the three methods of delineating zones can all decrease the variance of the crop nutrients, wheat spectral parameters and yield within the different zones. Considering the consistent relationship between the crop nutrients, wheat yield and the wheat spectral parameters, satellite remote sensing shows promise as a tool for assessing the variation in soil properties and yield in arable fields. The results of this study suggest that management zone delineation using RS data was reliable and feasible.     

Prediction of plant water status in almond and walnut trees using a continuous leaf monitoring system

Persistent drought conditions in the Central valley of California demands efficient irrigation scheduling tools such as precision or variable rate irrigation (VRI). To assist VRI scheduling, an experiment was conducted in almond and walnut orchards using a sensor system called ‘leaf monitor’, which was developed at UC Davis to detect plant water status. A Modified Crop Water Stress Index (MCWSI) was calculated to quantify plant water status using leaf temperature and environmental data collected by the leaf monitor. This technique also took into account spatio-temporal variability of plant water status. Stem water potential (SWP), which is considered a standard method for determining plant water stress (PWS), was also measured simultaneously. Relationships between measured deficit stem water potential (DSWP), which is the difference between SWP and the saturated baseline, and MCWSI were developed for both crops based on data collected during the 2013 and 2014 growing seasons. A linear relationship was found in the case of walnut crop with a coefficient of determination (r²) value of 0.67. A quadratic relationship was found in the case of almonds with a coefficient of multiple determination (R²) value of 0.75. Moreover, these results highlighted that at lower PWS of below 0.5 MPa of DSWP, almonds crops did not show any decrease in transpiration rate. However, when the stress level exceeded 0.5 MPa of DSWP, transpiration rate tended to decrease. On the other hand, walnut crop showed decrease in transpiration rate even at low PWS of below 0.5 MPa of DSWP. Temporal variability was noticed in PWS as it was found that coefficients of saturation baseline used for MCWSI method changed significantly throughout the season. MCWSI values estimated before an irrigation event was used to calculate the irrigation amount for low frequency variable rate irrigation (VRI) based on the relationship found between MCWSI and DSWP, and VRI led to an average 39% reduction in water usage as compared to the fixed 100% ET replacement irrigation method for all trees. Based on the results, leaf monitor showed potential for use as an irrigation scheduling tool.

     

Simulating winter wheat development response to temperature: Modifying Malo's exponential sine equation

Predicting crop developmental events is fundamental to simulation models and crop management decisions. Many approaches to predict developmental events have been developed, however, most only simulate the mean time for reaching a developmental event. An exponential sine equation developed by Malo [Malo, J.E., 2002. Modelling unimodal flowering phenology with exponential sine equation. Funct. Ecol. 16, 413–418] to predict flower number over time was modified to incorporate the response of crop development rate to temperature. The revised model (ExpSine model) uses the base, optimum, and maximum cardinal temperatures specific to a crop or genotype. Most model parameters were estimated from the literature, and four of the five model parameters have physiological significance. Model evaluation for winter wheat (Triticum aestivum L.) was based on two controlled environment studies from the literature and two field experiments conducted in the North China Plain (NCP) and the Tibet Plateau (TPC). The r² for the modified temperature response function was 0.74 and 0.91 for two different experiments and compared very well (identical mean r²'s) to an existing function (Beta model) [Yin, X., Kropff, M.J., McLaren, G., Visperas, R.M., 1995. A nonlinear model for crop development rate as a function of temperature. Agric. Forest Meteorol. 77, 1–16]. Differences between observed and predicted flowering dates ranged from −2 to 3 days in the NCP and from −7 to 4 days on the TPC, with the mean percent error in both sites less than 1% and no apparent bias observed in the model. This modification of Malo's exponential sine equation expanded the predictive ability of the original equation to simulate phenology across a broader range of environments. The ExpSine model developed can be used as a phenological module in various crop or ecological simulation models.     

An artificial neural network model for estimating Mentha crop biomass yield using Landsat 8 OLI

Yield forecasting is essential for management of the food and agriculture economic growth of a country. Artificial Neural Network (ANN) based models have been used widely to make precise and realistic forecasts, especially for the nonlinear and complicated problems like crop yield prediction, biomass change detection and crop evapo-transpiration examination. In the present study, various parameters viz. spectral bands of Landsat 8 OLI (Operational Land Imager) satellite data and derived spectral indices along with field inventory data were evaluated for Mentha crop biomass estimation using ANN technique of Multilayer Perceptron. The estimated biomass showed a good relationship (R²?=?0.762 and root mean square error (RMSE)?=?2.74 t/ha) with field-measured biomass.

     

Crop height variability detection in a single field by multi-temporal terrestrial laser scanning

Information on crop height, crop growth and biomass distribution is important for crop management and environmental modelling. For the determination of these parameters, terrestrial laser scanning in combination with real-time kinematic GPS (RTK–GPS) measurements was conducted in a multi-temporal approach in two consecutive years within a single field. Therefore, a time-of-flight laser scanner was mounted on a tripod. For georeferencing of the point clouds, all eight to nine positions of the laser scanner and several reflective targets were measured by RTK–GPS. The surveys were carried out three to four times during the growing periods of 2008 (sugar-beet) and 2009 (mainly winter barley). Crop surface models were established for every survey date with a horizontal resolution of 1 m, which can be used to derive maps of plant height and plant growth. The detected crop heights were consistent with observations from panoramic images and manual measurements (R² = 0.53, RMSE = 0.1 m). Topographic and soil parameters were used for statistical analysis of the detected variability of crop height and significant correlations were found. Regression analysis (R² < 0.31) emphasized the uncertainty of basic relations between the selected parameters and crop height variability within one field. Likewise, these patterns compared with the normalized difference vegetation index (NDVI) derived from satellite imagery show only minor significant correlations (r < 0.44).