Search

Demand for spring onion seeds is variable and maintaining its supply is crucial to the success of seed companies. Spring onion seed demand forecasting, which can help reduce the high operational costs increased by long-period propagation and complex logistics, has not previously been investigated yet. This paper provides a novel perspective on spring onion seed demand forecasting and proposes a hybrid Holt-Winters and support vector machine (SVM) forecasting model. The model uses dynamic factors, including historical seed sales, seed inventory, spring onion crop market price and weather data, as inputs to forecast spring onion seed demand. Forecasting error, i.e. the difference between actual and forecasted demand, is assessed. Two advanced machine learning models are trained on the same dataset as benchmark models. Numerical experiments using actual commercial sales data for three spring onion seed varieties show the proposed hybrid model outperformed the statistical-based models for all three forecasting errors. Seed inventory, spring onion crop market price and historical seed sales are the most important dynamic factors, among which seed inventory has short-term influence while other two have mid-term influence on seed demand forecasting. The absolute minimum temperature is the only factor having long-term influence. This study provides a promising spring onion seed demand forecasting model that helps understand the relationships between seed demand and other dynamic factors and the model could potentially be applied to demand forecasting of other crop seeds to reduce total operational costs. [ABSTRACT FROM AUTHOR]

This paper highlights the importance of optimized shape index for agricultural management system analysis that utilizes the contiguous bands of hyperspectral data to define the gradient of the spectral curve and improve image classification accuracy. Currently, a number of machine learning methods would resort to using averaged spectral information over wide bandwidths resulting in loss of crucial information available in those contiguous bands. The loss of information could mean a drop in the discriminative power when it comes to land cover classes with comparable spectral responses, as in the case of cultivated fields versus fallow lands. In this study, we proposed and tested three new optimized novel algorithms based on Moment Distance Index (MDI) that characterizes the whole shape of the spectral curve. The image classification tests conducted on two publicly available hyperspectral data sets (AVIRIS 1992 Indian Pine and HYDICE Washington DC Mall images) showed the robustness of the optimized algorithms in terms of classification accuracy. We achieved an overall accuracy of 98% and 99% for AVIRIS and HYDICE, respectively. The optimized indices were also time efficient as it avoided the process of band dimension reduction, such as those implemented by several well-known classifiers. Our results showed the potential of optimized shape indices, specifically the Moment Distance Ratio Right/Left (MDRRL), to discriminate between types of tillage (corn-min and corn-notill) and between grass/pasture and grass/trees, tree and grass under object-based random forest approach. [ABSTRACT FROM AUTHOR]

Studying soil nutrient variability and its effect on the growth and development of crops under a traditional tillage mode is the foundation for comprehensively implementing precision agriculture policies at the field scale and ensuring excellent crop management. In this paper, a 28.5 hm2 winter wheat field under the traditional cultivation model in Tianzhuang town of Huantai County was selected as the research area. The mesh point method was utilized for sampling (60×60 m), and the characteristics of soil available nitrogen (AN), available phosphorus (AP) and available potassium (AK) variations in the before sowing, reviving, jointing, and filling stages of winter wheat were analyzed using geostatistical and GIS methods. Moreover, Pearson correlation analysis was used to study the response of wheat growth and development to soil nutrient variations. As the growth stages progressed, 1) each nutrient showed the characteristics of low-high-low and moderate variability. The highest AN and AK contents were found at the reviving stage, while AP reached a turning point at the jointing stage. The order of variability of each nutrient was AN>AP>AK. 2) The nutrient variations first increased and then decreased and showed medium to strong spatial correlation. The three nutrients were strongly spatially correlated in the before sowing stage and moderately spatially correlated during the reviving stage. During the jointing and filling stages, AN had moderate spatial correlation, and AP and AK had strong spatial correlation. The spatial correlation of each nutrient was the weakest in the reviving stage, and the spatial correlation of AN was strongest in the before sowing stage, while the spatial correlations of AP and AK were strongest in the jointing stage. The spatial correlation of each soil nutrient decreased from the before sowing stage to the reviving stage and from the jointing stage to the filling stage, and the spatial correlation increased from the reviving stage to the jointing stage. 3) The soil nutrient content first increased and then decreased, and the grades of the nutrients gradually decreased. 4) The correlation between soil nutrients and wheat growth gradually increased. AN had the highest correlation with wheat growth, followed by AK and AP. The effect of soil nutrients on the growth of wheat at the reviving stage was greater than the effect of nutrients in the current stage. The growth of wheat at the jointing stage was mainly influenced by nutrients in the current stage, while the growth of wheat at the filling stage was influenced by the nutrient contents of both the previous and current stages. Thus, the date of fertilizer supplementation should be postponed properly. In this study, the soil nutrient dynamics and their influence on the growth of wheat during the winter wheat growth period under the traditional field model were well described, and these results could provide a theoretical basis for the precision management of soil nutrients in the northern winter wheat area where the planting environment and cultivation management are relatively uniform. [ABSTRACT FROM AUTHOR]

Appropriate Site Specific Weed Management (SSWM) is crucial to ensure the crop yields. Within SSWM of large-scale area, remote sensing is a key technology to provide accurate weed distribution information. Compared with satellite and piloted aircraft remote sensing, unmanned aerial vehicle (UAV) is capable of capturing high spatial resolution imagery, which will provide more detailed information for weed mapping. The objective of this paper is to generate an accurate weed cover map based on UAV imagery. The UAV RGB imagery was collected in 2017 October over the rice field located in South China. The Fully Convolutional Network (FCN) method was proposed for weed mapping of the collected imagery. Transfer learning was used to improve generalization capability, and skip architecture was applied to increase the prediction accuracy. After that, the performance of FCN architecture was compared with Patch_based CNN algorithm and Pixel_based CNN method. Experimental results showed that our FCN method outperformed others, both in terms of accuracy and efficiency. The overall accuracy of the FCN approach was up to 0.935 and the accuracy for weed recognition was 0.883, which means that this algorithm is capable of generating accurate weed cover maps for the evaluated UAV imagery. [ABSTRACT FROM AUTHOR]

Crop cultivar identification is fundamental for agricultural research, industry and policies. This paper investigates the feasibility of using visible/near infrared hyperspectral data collected with a miniaturized NIR spectrometer to identify cultivars of barley, chickpea and sorghum in the context of Ethiopia. A total of 2650 grains of barley, chickpea and sorghum cultivars were scanned using the SCIO, a recently released miniaturized NIR spectrometer. The effects of data preprocessing techniques and choosing a machine learning algorithm on distinguishing cultivars are further evaluated. Predictive multiclass models of 24 barley cultivars, 19 chickpea cultivars and 10 sorghum cultivars delivered an accuracy of 89%, 96% and 87% on hold-out sample. The Support Vector Machine (SVM) and Partial least squares discriminant analysis (PLS-DA) algorithms consistently outperformed other algorithms. Several cultivars, believed to be widely adopted in Ethiopia, were identified with perfect accuracy. These results advance the discussion on cultivar identification survey methods by demonstrating that miniaturized NIR spectrometers represent a low-cost, rapid and viable tool. We further discuss the potential utility of the method for adoption surveys, field-scale agronomic studies, socio-economic impact assessments and value chain quality control. Finally, we provide a free tool for R to easily carry out crop cultivar identification and measure uncertainty based on spectral data. [ABSTRACT FROM AUTHOR]

The aim of this work was to develop a method for selection of optimal soybean varieties for the American Midwest using data analytics. We extracted the knowledge about 174 varieties from the dataset, which contained information about weather, soil, yield and regional statistical parameters. Next, we predicted the yield of each variety in each of 6,490 observed subregions of the Midwest. Furthermore, yield was predicted for all the possible weather scenarios approximated by 15 historical weather instances contained in the dataset. Using predicted yields and covariance between varieties through different weather scenarios, we performed portfolio optimisation. In this way, for each subregion, we obtained a selection of varieties, that proved superior to others in terms of the amount and stability of yield. According to the rules of Syngenta Crop Challenge, for which this research was conducted, we aggregated the results across all subregions and selected up to five soybean varieties that should be distributed across the network of seed retailers. The work presented in this paper was the winning solution for Syngenta Crop Challenge 2017. [ABSTRACT FROM AUTHOR]

Using the spectrum data for quality prediction always suffers from noise and colinearity, so variable selection method plays an important role to deal with spectrum data. An efficient elastic net with regression coefficients method (Enet-BETA) is proposed to select the significant variables of the spectrum data in this paper. The proposed Enet-BETA method can not only select important variables to make the quality easy to interpret, but also can improve the stability and feasibility of the built model. Enet-BETA method is not prone to overfitting because of the reduction of redundant variables realized by elastic net method. Hypothesis testing is used to further simplify the model and provide a better insight into the nature of process. The experimental results prove that the proposed Enet-BETA method outperforms the other methods in terms of prediction performance and model interpretation. [ABSTRACT FROM AUTHOR]

Ganoderma boninense is a fungus that can affect oil palm trees and cause a serious disease called the basal stem root (BSR). This disease causes the death of more than 80% of oil palm trees midway through their economic life and hexaconazole is one of the particular fungicides that can control this fungus. Hexaconazole can be applied by the soil drenching method and it will be of interest to know the concentration of the residue in the soil after treatment with respect to time. Hence, a field study was conducted in order to determine the actual concentration of hexaconazole in soil. In the present paper, a new approach that can be used to predict the concentration of pesticides in the soil is proposed. The statistical analysis revealed that the Exploratory Data Analysis (EDA) techniques would be appropriate in this study. The EDA techniques were used to fit a robust resistant model and predict the concentration of the residue in the topmost layer of the soil. [ABSTRACT FROM AUTHOR]

Hybridization is frequent in the large and ecologically significant genus Carex (Cyperaceae). In four important sections of the northern regions (Ceratocystis, Glareosae, Phacocystis and Vesicariae), the frequent occurrence of hybrids often renders the identification of “pure” species and hybrids difficult. In this study we address the origins and taxonomic rank of two taxa of section Vesicariae: Carex rostrata var. borealis and C. stenolepis. The origin and taxonomic status of C. stenolepis has been the subject of substantial debate over the years, whereas C. rostrata var. borealis has received very little attention in the years since its first description in the 19th century. By performing an extensive sampling of relevant taxa from a broad distribution range, and analyzing data from fifteen microsatellite loci developed specifically for our study together with pollen stainability measures, we resolve the hybrid origins of C. rostrata var. borealis and C. stenolepis and provide new insights into this taxonomically challenging group of sedges. Our results are in accordance with previous findings suggesting that C. stenolepis is a hybrid between C. vesicaria and C. saxatilis. They are also in accordance with a previous proposition that C. rostrata var. borealis is a hybrid between C. rostrata and C. rotundata, and furthermore suggest that both hybrids are the result of multiple, recent (i.e., postglacial) hybridization events. We found little evidence for successful sexual reproduction within C. rostrata var. borealis and C. stenolepis, but conclude that the common and recurrent, largely predictable occurrence of these taxa justifies accepting both hybrids as hybrid species with binomial names. There are, however, complications as to types and priority names, and we therefore choose to address these problems in a separate paper. [ABSTRACT FROM AUTHOR]

The prediction of phenotypic traits using high-density genomic data has many applications such as the selection of plants and animals of commercial interest; and it is expected to play an increasing role in medical diagnostics. Statistical models used for this task are usually tested using cross-validation, which implicitly assumes that new individuals (whose phenotypes we would like to predict) originate from the same population the genomic prediction model is trained on. In this paper we propose an approach based on clustering and resampling to investigate the effect of increasing genetic distance between training and target populations when predicting quantitative traits. This is important for plant and animal genetics, where genomic selection programs rely on the precision of predictions in future rounds of breeding. Therefore, estimating how quickly predictive accuracy decays is important in deciding which training population to use and how often the model has to be recalibrated. We find that the correlation between true and predicted values decays approximately linearly with respect to either FST or mean kinship between the training and the target populations. We illustrate this relationship using simulations and a collection of data sets from mice, wheat and human genetics. [ABSTRACT FROM AUTHOR]

Introduction: More than 80% of all smokeless tobacco (ST) products in the world are consumed in South Asia; yet little is known about their consumption behaviour, addictiveness, and toxic properties. This paper, for the first time, describes associations between salivary cotinine concentrations among ST users in Bangladesh and their socio-demographic characteristics and tobacco use behaviours. Methods: In a survey of ST users in Dhaka, Bangladesh, we purposively recruited 200 adults who were non-smokers but consumed ST on a regular basis. In-person interviews were conducted to obtain information about socio-demographic and ST use behaviours, and saliva samples were collected to measure cotinine concentration. Simple and multiple linear regression analyses were conducted to test associations between the log transformed salivary cotinine concentration and other study variables. Results: The geometric mean of cotinine concentration among ST users was 380ng/ml (GSD:2). Total duration of daily ST use in months had a statistically significant association with cotinine concentration. Other ST use characteristics including type and quantity of ST use, swallowing of tobacco juice, urges and strength of urges and attempts to cut down on tobacco use were not found to be associated with cotinine concentration in a multivariable model. Conclusion: This is the first report from Bangladesh studying cotinine concentration among ST users and it points towards high levels of addiction. This warrants effective tobacco control policies to help ST cessation and prevention. [ABSTRACT FROM AUTHOR]

Introduction: Agricultural technologies developed by national and international research institutions were not benefiting the rural population of Ethiopia to the extent desired. As a response, integrated agricultural extension approaches are proposed as a key strategy to transform the smallholder farming sector. Improving Productivity and Market Success (IPMS) of Ethiopian Farmers project is one of the development projects initiated by integrating productivity enhancement technological schemes with market development model. This paper explores the impact of the project intervention in the smallholder farmers’ wellbeing. Methods: To test the research hypothesis of whether the project brought a significant change in the input use, marketed surplus, efficiency and income of farm households, we use a cross-section data from 200 smallholder farmers in Northwest Ethiopia, collected through multi-stage sampling procedure. To control for self-selection from observable characteristics of the farm households, we employ Propensity Score Matching (PSM). We finally use Data Envelopment Analysis (DEA) techniques to estimate technical efficiency of farm households. Results: The outcome of the research is in line with the premises that the participation of the household in the IPMS project improves purchased input use, marketed surplus, efficiency of farms and the overall gain from farming. The participant households on average employ more purchased agricultural inputs and gain higher gross margin from the production activities as compared to the non-participant households. The non-participant households on average supply less output (measured both in monetary terms and proportion of total produce) to the market as compared to their participant counterparts. Except for the technical efficiency of production in potato, project participant households are better-off in production efficiency compared with the non-participant counterparts. Conclusion: We verified the idea that Improving Productivity and Market Success (IPMS) of Ethiopian farmers’ project has contributed for the input and out market integration and/or market oriented agricultural production. Overall, we argue that these can be seen as an experimental model with a promising potential to improve the livelihood of the poor. Furthermore, we suggest that it is worthwhile to employ integrated agricultural extension programs with further targeting in the developing world. [ABSTRACT FROM AUTHOR]

Information on an organism’s body size is pivotal in understanding its life history and fitness, as well as helping inform conservation measures. However, for many species, particularly large-bodied wild animals, taking accurate body size measurements can be a challenge. Various means to estimate body size have been employed, from more direct methods such as using photogrammetry to obtain height or length measurements, to indirect prediction of weight using other body morphometrics or even the size of dung boli. It is often unclear how accurate these measures are because they cannot be compared to objective measures. Here, we investigate how well existing estimation equations predict the actual body weight of Asian elephants Elephas maximus, using body measurements (height, chest girth, length, foot circumference and neck circumference) taken directly from a large population of semi-captive animals in Myanmar (n = 404). We then define new and better fitting formulas to predict body weight in Myanmar elephants from these readily available measures. We also investigate whether the important parameters height and chest girth can be estimated from photographs (n = 151). Our results show considerable variation in the ability of existing estimation equations to predict weight, and that the equations proposed in this paper predict weight better in almost all circumstances. We also find that measurements from standardised photographs reflect body height and chest girth after applying minor adjustments. Our results have implications for size estimation of large wild animals in the field, as well as for management in captive settings. [ABSTRACT FROM AUTHOR]

Several variable selection algorithms in multivariate calibration can be accelerated using Graphics Processing Units (GPU). Among these algorithms, the Firefly Algorithm (FA) is a recent proposed metaheuristic that may be used for variable selection. This paper presents a GPU-based FA (FA-MLR) with multiobjective formulation for variable selection in multivariate calibration problems and compares it with some traditional sequential algorithms in the literature. The advantage of the proposed implementation is demonstrated in an example involving a relatively large number of variables. The results showed that the FA-MLR, in comparison with the traditional algorithms is a more suitable choice and a relevant contribution for the variable selection problem. Additionally, the results also demonstrated that the FA-MLR performed in a GPU can be five times faster than its sequential implementation. [ABSTRACT FROM AUTHOR]