scholarly journals Advancing agricultural research using machine learning algorithms

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Spyridon Mourtzinis ◽  
Paul D. Esker ◽  
James E. Specht ◽  
Shawn P. Conley
Keyword(s):  
Management Practices ◽  
Agricultural Research ◽  
Cropping System ◽  
Weather Conditions ◽  
Machine Learning Algorithms ◽  
Complex Interactions ◽  
Traditional Research ◽  
The Us ◽  
Large Crop ◽  
Global Population

AbstractRising global population and climate change realities dictate that agricultural productivity must be accelerated. Results from current traditional research approaches are difficult to extrapolate to all possible fields because they are dependent on specific soil types, weather conditions, and background management combinations that are not applicable nor translatable to all farms. A method that accurately evaluates the effectiveness of infinite cropping system interactions (involving multiple management practices) to increase maize and soybean yield across the US does not exist. Here, we utilize extensive databases and artificial intelligence algorithms and show that complex interactions, which cannot be evaluated in replicated trials, are associated with large crop yield variability and thus, potential for substantial yield increases. Our approach can accelerate agricultural research, identify sustainable practices, and help overcome future food demands.

Testing the simulation capability of APSIM-ORYZA under different levels of nitrogen fertiliser and transplanting time regimes in Korea

2007 ◽  
Vol 47 (12) ◽  
pp. 1446 ◽  
Author(s):  
Xike Zhang ◽  
Jae-Hong Lee ◽  
Yahya Abawi ◽  
Young-ho Kim ◽  
David McClymont ◽  
...  
Keyword(s):  
Management Practices ◽  
Field Experiments ◽  
Agricultural Research ◽  
Cropping System ◽  
Measured Data ◽  
Rice Varieties ◽  
Early Maturing ◽  
Photoperiod Sensitive ◽  
Korean Rice ◽  
Management Issues

APSIM-ORYZA is a new functionality developed in the APSIM framework to simulate rice production while addressing management issues such as fertilisation and transplanting, which are particularly important in Korean agriculture. To validate the model for Korean rice varieties and field conditions, the measured yields and flowering times from three field experiments conducted by the Gyeonggi Agricultural Research and Extension Services (GARES) in Korea were compared against the simulated outputs for different management practices and rice varieties. Simulated yields of early-, mid- and mid-to-late-maturing varieties of rice grown in a continuous rice cropping system from 1997 to 2004 showed close agreement with the measured data. Similar results were also found for yields simulated under seven levels of nitrogen application. When different transplanting times were modelled, simulated flowering times ranged from within 3 days of the measured values for the early-maturing varieties, to up to 9 days after the measured dates for the mid- and especially mid-to-late-maturing varieties. This was associated with highly variable simulated yields which correlated poorly with the measured data. This suggests the need to accurately calibrate the photoperiod sensitivity parameters of the model for the photoperiod-sensitive rice varieties in Korea.

scholarly journals Impact of Safe Rock® Minerals, Mineral Fertilizers, and Manure on the Quantity and Quality of the Wheat Yield in the Rice–Wheat Cropping System

Plants ◽  
2022 ◽  
Vol 11 (2) ◽  
pp. 183
Author(s):  
Santosh Ranva ◽  
Yudh Vir Singh ◽  
Neelam Jain ◽  
Ram Swaroop Bana ◽  
Ramesh Chand Bana ◽  
...  
Keyword(s):  
Management Practices ◽  
Agricultural Research ◽  
Indian Agricultural Research Institute ◽  
Wheat Yield ◽  
Growth Yield ◽  
Cropping System ◽  
Mineral Fertilizers ◽  
Yield Attributes ◽  
Natural Rock ◽  
The Impact

Rice–wheat (RW) rotation is the largest agriculture production system in South Asia with a multifaceted role in maintaining the livelihood of people. The customary practices and indiscriminate use of synthetic fertilizers have culminated in the decline of its productivity and profitability during the past two decades, thus affecting the sustainability of wheat. Safe Rock® Minerals (SRM) is a multi-nutrient rich natural rock mineral with great potential to manage soil degradation, reducing the input of fertilizers, improving soil fertility, and plant health. Thus, a field trial was conducted at the research farm of ICAR—Indian Agricultural Research Institute, New Delhi from 2016 to 2018 to evaluate the impact of Safe Rock® Minerals (SRM) on biometric parameters, productivity, quality, and nutrient uptake by conventional wheat and System of Wheat Intensification (SWI) in the wheat–rice cropping system. The results indicate that SWI performed better in terms of growth, yield, and quality parameters than conventional wheat. Among nutrient management practices; the highest growth, yield, and yield attributes of wheat were achieved with the use of SRM application 250 kg ha−1 + 100% Recommended Dose of Fertilizer (RDF). SRM application also increased grain protein content significantly. In conclusion, the integrated use of SRM with organic manures can serve as an eco-friendly approach for sustainable wheat production.

Nitrate Leaching to a Shallow Mid-Atlantic Coastal Plain Aquifer as Influenced by Conventional No-Till and Low-Input Sustainable Grain Production Systems

1993 ◽  
Vol 28 (3-5) ◽  
pp. 691-700 ◽  
Author(s):  
J. P. Craig ◽  
R. R. Weil
Keyword(s):  
Management Practices ◽  
Production Systems ◽  
Cropping Systems ◽  
Cropping System ◽  
Atlantic Coastal Plain ◽  
Grain Production ◽  
Nitrogen And Phosphorus ◽  
Mineral N ◽  
Low Input ◽  
No Till

In December, 1987, the states in the Chesapeake Bay region, along with the federal government, signed an agreement which called for a 40% reduction in nitrogen and phosphorus loadings to the Bay by the year 2000. To accomplish this goal, major reductions in nutrient loadings associated with agricultural management practices were deemed necessary. The objective of this study was to determine if reducing fertilizer inputs to the NT system would result in a reduction in nitrogen contamination of groundwater. In this study, groundwater, soil, and percolate samples were collected from two cropping systems. The first system was a conventional no-till (NT) grain production system with a two-year rotation of corn/winter wheat/double crop soybean. The second system, denoted low-input sustainable agriculture (LISA), produced the same crops using a winter legume and relay-cropped soybeans into standing wheat to reduce nitrogen and herbicide inputs. Nitrate-nitrogen concentrations in groundwater were significantly lower under the LISA system. Over 80% of the NT groundwater samples had NO3-N concentrations greater than 10 mgl-1, compared to only 4% for the LISA cropping system. Significantly lower soil mineral N to a depth of 180 cm was also observed. The NT soil had nearly twice as much mineral N present in the 90-180 cm portion than the LISA cropping system.

scholarly journals Using Machine Learning Methods to Identify Particle Types from Doppler Lidar Measurements in Iceland

2021 ◽  
Vol 13 (13) ◽  
pp. 2433
Author(s):  
Shu Yang ◽  
Fengchao Peng ◽  
Sibylle von Löwis ◽  
Guðrún Nína Petersen ◽  
David Christian Finger
Keyword(s):  
Machine Learning ◽  
Weather Conditions ◽  
Dust Storms ◽  
Machine Learning Algorithms ◽  
Lidar Data ◽  
Data Sets ◽  
Doppler Lidar ◽  
Lidar Measurements ◽  
Using Data ◽  
Filter Noise

Doppler lidars are used worldwide for wind monitoring and recently also for the detection of aerosols. Automatic algorithms that classify the lidar signals retrieved from lidar measurements are very useful for the users. In this study, we explore the value of machine learning to classify backscattered signals from Doppler lidars using data from Iceland. We combined supervised and unsupervised machine learning algorithms with conventional lidar data processing methods and trained two models to filter noise signals and classify Doppler lidar observations into different classes, including clouds, aerosols and rain. The results reveal a high accuracy for noise identification and aerosols and clouds classification. However, precipitation detection is underestimated. The method was tested on data sets from two instruments during different weather conditions, including three dust storms during the summer of 2019. Our results reveal that this method can provide an efficient, accurate and real-time classification of lidar measurements. Accordingly, we conclude that machine learning can open new opportunities for lidar data end-users, such as aviation safety operators, to monitor dust in the vicinity of airports.

scholarly journals Assessing Opportunities to Increase Yield and Profit in Rainfed Lowland Rice Systems in Indonesia

Agronomy ◽  
2021 ◽  
Vol 11 (4) ◽  
pp. 777
Author(s):  
Erythrina Erythrina ◽  
Arif Anshori ◽  
Charles Y. Bora ◽  
Dina O. Dewi ◽  
Martina S. Lestari ◽  
...  
Keyword(s):  
Best Management Practices ◽  
Management Practices ◽  
Nutrient Management ◽  
Agricultural Research ◽  
Rice Yield ◽  
Information Access ◽  
Water Reservoir ◽  
Dry Season ◽  
Rice Production ◽  
Yield Gap

In this study, we aimed to improve rice farmers’ productivity and profitability in rainfed lowlands through appropriate crop and nutrient management by closing the rice yield gap during the dry season in the rainfed lowlands of Indonesia. The Integrated Crop Management package, involving recommended practices (RP) from the Indonesian Agency for Agricultural Research and Development (IAARD), were compared to the farmers’ current practices at ten farmer-participatory demonstration plots across ten provinces of Indonesia in 2019. The farmers’ practices (FP) usually involved using old varieties in their remaining land and following their existing fertilizer management methods. The results indicate that improved varieties and nutrient best management practices in rice production, along with water reservoir infrastructure and information access, contribute to increasing the productivity and profitability of rice farming. The mean rice yield increased significantly with RP compared with FP by 1.9 t ha–1 (ranges between 1.476 to 2.344 t ha–1), and net returns increased, after deducting the cost of fertilizers and machinery used for irrigation supplements, by USD 656 ha–1 (ranges between USD 266.1 to 867.9 ha–1) per crop cycle. This represents an exploitable yield gap of 37%. Disaggregated by the wet climate of western Indonesia and eastern Indonesia’s dry climate, the RP increased rice productivity by 1.8 and 2.0 t ha–1, with an additional net return gain per cycle of USD 600 and 712 ha–1, respectively. These results suggest that there is considerable potential to increase the rice production output from lowland rainfed rice systems by increasing cropping intensity and productivity. Here, we lay out the potential for site-specific variety and nutrient management with appropriate crop and supplemental irrigation as an ICM package, reducing the yield gap and increasing farmers’ yield and income during the dry season in Indonesia’s rainfed-prone areas.

scholarly journals Low HbA1c levels and all-cause or cardiovascular mortality among people without diabetes: the US National Health and Nutrition Examination Survey 1999–2015

2020 ◽  
Author(s):  
Kosuke Inoue ◽  
Roch Nianogo ◽  
Donatello Telesca ◽  
Atsushi Goto ◽  
Vahe Khachadourian ◽  
...  
Keyword(s):  
Cardiovascular Mortality ◽  
Regression Models ◽  
Machine Learning Algorithms ◽  
Logistic Regression Models ◽  
Health And Nutrition ◽  
Increased Risk ◽  
The Us ◽  
All Cause Mortality ◽  
Hba1c Levels

Abstract Objective It is unclear whether relatively low glycated haemoglobin (HbA1c) levels are beneficial or harmful for the long-term health outcomes among people without diabetes. We aimed to investigate the association between low HbA1c levels and mortality among the US general population. Methods This study includes a nationally representative sample of 39 453 US adults from the National Health and Nutrition Examination Surveys 1999–2014, linked to mortality data through 2015. We employed the parametric g-formula with pooled logistic regression models and the ensemble machine learning algorithms to estimate the time-varying risk of all-cause and cardiovascular mortality by HbA1c categories (low, 4.0 to <5.0%; mid-level, 5.0 to <5.7%; prediabetes, 5.7 to <6.5%; and diabetes, ≥6.5% or taking antidiabetic medication), adjusting for 72 potential confounders including demographic characteristics, lifestyle, biomarkers, comorbidities and medications. Results Over a median follow-up of 7.5 years, 5118 (13%) all-cause deaths, and 1116 (3%) cardiovascular deaths were observed. Logistic regression models and machine learning algorithms showed nearly identical predictive performance of death and risk estimates. Compared with mid-level HbA1c, low HbA1c was associated with a 30% (95% CI, 16 to 48) and a 12% (95% CI, 3 to 22) increased risk of all-cause mortality at 5 years and 10 years of follow-up, respectively. We found no evidence that low HbA1c levels were associated with cardiovascular mortality risk. The diabetes group, but not the prediabetes group, also showed an increased risk of all-cause mortality. Conclusions Using the US national database and adjusting for an extensive set of potential confounders with flexible modelling, we found that adults with low HbA1c were at increased risk of all-cause mortality. Further evaluation and careful monitoring of low HbA1c levels need to be considered.

scholarly journals Prediction of Pest Insect Appearance Using Sensors and Machine Learning

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4846
Author(s):  
Dušan Marković ◽  
Dejan Vujičić ◽  
Snežana Tanasković ◽  
Borislav Đorđević ◽  
Siniša Ranđić ◽  
...  
Keyword(s):  
Machine Learning ◽  
Relative Humidity ◽  
Weather Conditions ◽  
Daily Basis ◽  
Machine Learning Algorithms ◽  
Lower Percentage ◽  
Timely Manner ◽  
Proposed Model ◽  
Set Up ◽  
Accuracy Of Prediction

The appearance of pest insects can lead to a loss in yield if farmers do not respond in a timely manner to suppress their spread. Occurrences and numbers of insects can be monitored through insect traps, which include their permanent touring and checking of their condition. Another more efficient way is to set up sensor devices with a camera at the traps that will photograph the traps and forward the images to the Internet, where the pest insect’s appearance will be predicted by image analysis. Weather conditions, temperature and relative humidity are the parameters that affect the appearance of some pests, such as Helicoverpa armigera. This paper presents a model of machine learning that can predict the appearance of insects during a season on a daily basis, taking into account the air temperature and relative humidity. Several machine learning algorithms for classification were applied and their accuracy for the prediction of insect occurrence was presented (up to 76.5%). Since the data used for testing were given in chronological order according to the days when the measurement was performed, the existing model was expanded to take into account the periods of three and five days. The extended method showed better accuracy of prediction and a lower percentage of false detections. In the case of a period of five days, the accuracy of the affected detections was 86.3%, while the percentage of false detections was 11%. The proposed model of machine learning can help farmers to detect the occurrence of pests and save the time and resources needed to check the fields.

scholarly journals Earthworm Abundance Changes Depending on Soil Management Practices in Slovenian Vineyards

Agronomy ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1241
Author(s):  
Stanko Vršič ◽  
Marko Breznik ◽  
Borut Pulko ◽  
Jesús Rodrigo-Comino
Keyword(s):  
Management Practices ◽  
Human Impacts ◽  
Soil Layer ◽  
Soil Management ◽  
Weather Conditions ◽  
Soil Tillage ◽  
Soil Biodiversity ◽  
Straw Mulch ◽  
Green Cover ◽  
The Impact

Earthworms are key indicators of soil quality and health in vineyards, but research that considers different soil management systems, especially in Slovenian viticultural areas is scarce. In this investigation, the impact of different soil management practices such as permanent green cover, the use of herbicides in row and inter-row areas, use of straw mulch, and shallow soil tillage compared to meadow control for earthworm abundance, were assessed. The biomass and abundance of earthworms (m2) and distribution in various soil layers were quantified for three years. Monitoring and a survey covering 22 May 2014 to 5 October 2016 in seven different sampling dates, along with a soil profile at the depth from 0 to 60 cm, were carried out. Our results showed that the lowest mean abundance and biomass of earthworms in all sampling periods were registered along the herbicide strip (within the rows). The highest abundance was found in the straw mulch and permanent green cover treatments (higher than in the control). On the plots where the herbicide was applied to the complete inter-row area, the abundance of the earthworm community decreased from the beginning to the end of the monitoring period. In contrast, shallow tillage showed a similar trend of declining earthworm abundance, which could indicate a deterioration of soil biodiversity conditions. We concluded that different soil management practices greatly affect the soil’s environmental conditions (temperature and humidity), especially in the upper soil layer (up to 15 cm deep), which affects the abundance of the earthworm community. Our results demonstrated that these practices need to be adapted to the climate and weather conditions, and also to human impacts.

scholarly journals Prediction of Healing Performance of Autogenous Healing Concrete Using Machine Learning

Materials ◽  
2021 ◽  
Vol 14 (15) ◽  
pp. 4068
Author(s):  
Xu Huang ◽  
Mirna Wasouf ◽  
Jessada Sresakoolchai ◽  
Sakdirat Kaewunruen
Keyword(s):  
Machine Learning ◽  
Search Algorithm ◽  
Weather Conditions ◽  
Prediction Performance ◽  
Machine Learning Algorithms ◽  
Coefficient Of Determination ◽  
Gradient Boosting ◽  
Support Vector ◽  
Self Healing ◽  
Artificial Neural Network Ann

Cracks typically develop in concrete due to shrinkage, loading actions, and weather conditions; and may occur anytime in its life span. Autogenous healing concrete is a type of self-healing concrete that can automatically heal cracks based on physical or chemical reactions in concrete matrix. It is imperative to investigate the healing performance that autogenous healing concrete possesses, to assess the extent of the cracking and to predict the extent of healing. In the research of self-healing concrete, testing the healing performance of concrete in a laboratory is costly, and a mass of instances may be needed to explore reliable concrete design. This study is thus the world’s first to establish six types of machine learning algorithms, which are capable of predicting the healing performance (HP) of self-healing concrete. These algorithms involve an artificial neural network (ANN), a k-nearest neighbours (kNN), a gradient boosting regression (GBR), a decision tree regression (DTR), a support vector regression (SVR) and a random forest (RF). Parameters of these algorithms are tuned utilising grid search algorithm (GSA) and genetic algorithm (GA). The prediction performance indicated by coefficient of determination (R2) and root mean square error (RMSE) measures of these algorithms are evaluated on the basis of 1417 data sets from the open literature. The results show that GSA-GBR performs higher prediction performance (R2GSA-GBR = 0.958) and stronger robustness (RMSEGSA-GBR = 0.202) than the other five types of algorithms employed to predict the healing performance of autogenous healing concrete. Therefore, reliable prediction accuracy of the healing performance and efficient assistance on the design of autogenous healing concrete can be achieved.

scholarly journals Developing Pavement Marking Management Systems: A Theoretical Model Framework Based on the Experiences of the US Transportation Agencies

2021 ◽  
Vol 6 (2) ◽  
pp. 18
Author(s):  
Alireza Sassani ◽  
Omar Smadi ◽  
Neal Hawkins
Keyword(s):  
Asset Management ◽  
Management Practices ◽  
Relevant Literature ◽  
Building Blocks ◽  
Management Systems ◽  
Model Framework ◽  
Pavement Markings ◽  
The Us ◽  
Pavement Marking ◽  
Transportation Agencies

Pavement markings are essential elements of transportation infrastructure with critical impacts on safety and mobility. They provide road users with the necessary information to adjust driving behavior or make calculated decisions about commuting. The visibility of pavement markings for drivers can be the boundary between a safe trip and a disastrous accident. Consequently, transportation agencies at the local or national levels allocate sizeable budgets to upkeep the pavement markings under their jurisdiction. Infrastructure asset management systems (IAMS) are often biased toward high-capital-cost assets such as pavements and bridges, not providing structured asset management (AM) plans for low-cost assets such as pavement markings. However, recent advances in transportation asset management (TAM) have promoted an integrated approach involving the pavement marking management system (PMMS). A PMMS brings all data items and processes under a comprehensive AM plan and enables managing pavement markings more efficiently. Pavement marking operations depend on location, conditions, and AM policies, highly diversifying the pavement marking management practices among agencies and making it difficult to create a holistic image of the system. Most of the available resources for pavement marking management focus on practices instead of strategies. Therefore, there is a lack of comprehensive guidelines and model frameworks for developing PMMS. This study utilizes the existing body of knowledge to build a guideline for developing and implementing PMMS. First, by adapting the core AM concepts to pavement marking management, a model framework for PMMS is created, and the building blocks and elements of the framework are introduced. Then, the caveats and practical points in PMMS implementation are discussed based on the US transportation agencies’ experiences and the relevant literature. This guideline is aspired to facilitate PMMS development for the agencies and pave the way for future pavement marking management tools and databases.

Sign in / Sign up

Export Citation Format

Share Document