scholarly journals Field Data Forecasting Using LSTM and Bi-LSTM Approaches

2021 ◽  
Vol 11 (24) ◽  
pp. 11820
Author(s):  
Paweena Suebsombut ◽  
Aicha Sekhari ◽  
Pradorn Sureephong ◽  
Abdelhak Belhi ◽  
Abdelaziz Bouras
Keyword(s):  
Soil Moisture ◽  
Crop Yield ◽  
Crop Production ◽  
Cross Validation ◽  
Short Term Memory ◽  
Weather Forecasting ◽  
Irrigation Scheduling ◽  
The Future ◽  
Cross Validation Error ◽  
Crop Irrigation

Water, an essential resource for crop production, is becoming increasingly scarce, while cropland continues to expand due to the world’s population growth. Proper irrigation scheduling has been shown to help farmers improve crop yield and quality, resulting in more sustainable water consumption. Soil Moisture (SM), which indicates the amount of water in the soil, is one of the most important crop irrigation parameters. In terms of water usage optimization and crop yield, estimating future soil moisture (forecasting) is an essentially valuable task for crop irrigation. As a result, farmers can base crop irrigation decisions on this parameter. Sensors can be used to estimate this value in real time, which may assist farmers in deciding whether or not to irrigate. The soil moisture value provided by the sensors, on the other hand, is instantaneous and cannot be used to directly compute irrigation parameters such as the best timing or the required water quantity to irrigate. The soil moisture value can, in fact, vary greatly depending on factors such as humidity, weather, and time. Using machine learning methods, these parameters can be used to predict soil moisture levels in the near future. This paper proposes a new Long-Short Term Memory (LSTM)-based model to forecast soil moisture values in the future based on parameters collected from various sensors as a potential solution. To train and validate this model, a real-world dataset containing a set of parameters related to weather forecasting, soil moisture, and other related parameters was collected using smart sensors installed in a greenhouse in Chiang Mai province, Thailand. Preliminary results show that our LSTM-based model performs well in predicting soil moisture with a 0.72% RMSE error and a 0.52% cross-validation error (LSTM), and our Bi-LSTM model with a 0.76% RMSE error and a 0.57% cross-validation error. In the future, we aim to test and validate this model on other similar datasets.

Usage of soil moisture models in agronomic research

1996 ◽  
Vol 76 (3) ◽  
pp. 285-295 ◽  
Author(s):  
O. O. Akinremi ◽  
S. M. McGinn
Keyword(s):  
Soil Moisture ◽  
Grain Yield ◽  
Water Use ◽  
Crop Yield ◽  
Drought Index ◽  
Regional Scale ◽  
Irrigation Scheduling ◽  
Water Model ◽  
Yield Reduction ◽  
Efficiency Coefficient

Soil moisture controls many important processes in the soil-plant system and the extent of these processes cannot be quantified without knowing moisture status of the root zone. Of agronomic importance these include, seedling emergence, evapotranspiration, mineralization of the soil organic fraction, surface runoff, leaching and crop yield. Many models have been developed to simulate these processes based on algorithms of varying degrees of complexity that describe the dynamic nature of soil moisture at different temporal and spatial scales. This paper reviews the direct applications of soil moisture models in agronomy from the field to regional scale and for daily to seasonal time steps. At every level of detail, the lack of model validation beyond the region where it was developed is the main limitation to the application of soil moisture models in agronomy. At the field scale, models have been used for irrigation scheduling to ensure efficient utilization of irrigation water and maximize crop yields. Models are also used to estimate crop yield based on the growing season water use. The water use of crops is converted to biomass accumulation and grain yield using a water-use efficiency coefficient and a harvest index. Other empirical equations are available that relate cumulative crop water use directly to grain yield. On a regional scale, in a study of drought climatology on the Canadian prairie, we coupled a soil water model, the Versatile Soil Moisture Budget, with the Palmer Drought Index model to improve the modelling of soil moisture. This was found to improve the relationship of the Palmer drought index to wheat yield reduction resulting from drought. Key words: Soil moisture, modelling, water-use, evapotranspiration, aridity index, Canadian prairies

scholarly journals Silica fertilization improved wheat performance and increased phosphorus concentrations during drought at the field scale

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Jörg Schaller ◽  
Eric Scherwietes ◽  
Lukas Gerber ◽  
Shrijana Vaidya ◽  
Danuta Kaczorek ◽  
...  
Keyword(s):  
Soil Moisture ◽  
Crop Production ◽  
Terrestrial Ecosystem ◽  
Fertilizer Application ◽  
Plant Performance ◽  
Phosphorus Concentration ◽  
Phosphorus Fertilizer ◽  
Field Scale ◽  
Promising Tool ◽  
The Future

AbstractDrought and the availability of mineable phosphorus minerals used for fertilization are two of the important issues agriculture is facing in the future. High phosphorus availability in soils is necessary to maintain high agricultural yields. Drought is one of the major threats for terrestrial ecosystem performance and crop production in future. Among the measures proposed to cope with the upcoming challenges of intensifying drought stress and to decrease the need for phosphorus fertilizer application is the fertilization with silica (Si). Here we tested the importance of soil Si fertilization on wheat phosphorus concentration as well as wheat performance during drought at the field scale. Our data clearly showed a higher soil moisture for the Si fertilized plots. This higher soil moisture contributes to a better plant performance in terms of higher photosynthetic activity and later senescence as well as faster stomata responses ensuring higher productivity during drought periods. The plant phosphorus concentration was also higher in Si fertilized compared to control plots. Overall, Si fertilization or management of the soil Si pools seem to be a promising tool to maintain crop production under predicted longer and more serve droughts in the future and reduces phosphorus fertilizer requirements.

scholarly journals Neural network models for soil moisture forecasting from remote sensed measurements

ACTA IMEKO ◽  
2020 ◽  
Vol 9 (2) ◽  
pp. 59
Author(s):  
Andrea Marini ◽  
Loris Francesco Termite ◽  
Alberto Garinei ◽  
Marcello Marconi ◽  
Lorenzo Biondi
Keyword(s):  
Neural Network ◽  
Soil Moisture ◽  
Short Term Memory ◽  
Meteorological Data ◽  
Network Models ◽  
Irrigation Scheduling ◽  
Machine Learning Techniques ◽  
Free Access ◽  
Neural Network Models ◽  
Inference System

Machine learning techniques are employed to describe the temporal behavior of soil moisture using meteorological data as inputs. Three different Artificial Neural Network models, a feedforward Multi-Layer Perceptron, a Long-Short Term Memory and the Adaptive Network-based Fuzzy Inference System, are trained and their results are compared. The soil moisture is expressed in terms of Soil Water Index, derived from satellite retrievals, with the last known value also being used as input. The results are promising as the proposed methodology relies on free-access data with a worldwide coverage, allowing to easily estimate the forthcoming soil moisture. The knowledge of the expected value of this variable could be extremely useful for irrigation scheduling and it is the basis of Decision Support Systems to efficiently manage water resources in agriculture.

scholarly journals Crop yield prediction integrating genotype and weather variables using deep learning

PLoS ONE ◽  
2021 ◽  
Vol 16 (6) ◽  
pp. e0252402
Author(s):  
Johnathon Shook ◽  
Tryambak Gangopadhyay ◽  
Linjiang Wu ◽  
Baskar Ganapathysubramanian ◽  
Soumik Sarkar ◽  
...  
Keyword(s):  
Crop Yield ◽  
Crop Production ◽  
Short Term Memory ◽  
Time Windows ◽  
Climatic Conditions ◽  
Support Vector ◽  
Yield Prediction ◽  
Lasso Regression ◽  
Important Time ◽  
Interpretable Models

Accurate prediction of crop yield supported by scientific and domain-relevant insights, is useful to improve agricultural breeding, provide monitoring across diverse climatic conditions and thereby protect against climatic challenges to crop production. We used performance records from Uniform Soybean Tests (UST) in North America to build a Long Short Term Memory (LSTM)—Recurrent Neural Network based model that leveraged pedigree relatedness measures along with weekly weather parameters to dissect and predict genotype response in multiple-environments. Our proposed models outperformed other competing machine learning models such as Support Vector Regression with Radial Basis Function kernel (SVR-RBF), least absolute shrinkage and selection operator (LASSO) regression and the data-driven USDA model for yield prediction. Additionally, for providing interpretability of the important time-windows in the growing season, we developed a temporal attention mechanism for LSTM models. The outputs of such interpretable models could provide valuable insights to plant breeders.

scholarly journals Improved Soil Moisture and Electrical Conductivity Prediction of Citrus Orchards Based on IoT Using Deep Bidirectional LSTM

Agriculture ◽  
2021 ◽  
Vol 11 (7) ◽  
pp. 635
Author(s):  
Peng Gao ◽  
Jiaxing Xie ◽  
Mingxin Yang ◽  
Ping Zhou ◽  
Wenbin Chen ◽  
...  
Keyword(s):  
Electrical Conductivity ◽  
Soil Moisture ◽  
Short Term Memory ◽  
Absolute Error ◽  
Irrigation Scheduling ◽  
Environmental Information ◽  
Performance Criteria ◽  
Coefficient Of Determination ◽  
Large Area ◽  
Citrus Orchards

In order to create an irrigation scheduling plan for use in large-area citrus orchards, an environmental information collection system of citrus orchards was established based on the Internet of Things (IoT). With the environmental information data, deep bidirectional long short-term memory (Bid-LSTM) networks are proposed to improve soil moisture (SM) and soil electrical conductivity (SEC) predictions, providing a meaningful reference for the irrigation and fertilization of citrus orchards. The IoT system contains SM, SEC, air temperature and humidity, wind speed, and precipitation sensors, while the mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2) were calculated to evaluate the performance of the models. The performance of the deep Bid-LSTM model was compared with a multi-layer neural network (MLNN). The results for the performance criteria reveal that the proposed deep Bid-LSTM networks perform better than the MLNN model, according to many of the evaluation indicators of this study.

scholarly journals Use of Irrigation Technologies for Vegetable Crops in Florida

2010 ◽  
Vol 20 (1) ◽  
pp. 133-142 ◽  
Author(s):  
Michael D. Dukes ◽  
Lincoln Zotarelli ◽  
Kelly T. Morgan
Keyword(s):  
Soil Moisture ◽  
Control Systems ◽  
Research Priorities ◽  
Irrigation Scheduling ◽  
Future Research ◽  
Vegetable Crops ◽  
Factors Affecting ◽  
Horticultural Crops ◽  
Wide Range ◽  
Crop Irrigation

Major horticultural crops in Florida are vegetables, small fruit, melons, and tree fruit crops. Approximately half of the agricultural area and nearly all of the horticultural crop land is irrigated. Irrigation systems include low-volume microirrigation, sprinkler systems, and subsurface irrigation. The present review was divided into two papers, in which the first part focuses on vegetable crop irrigation and the second part focuses on fruit tree crop irrigation. This first part also provides an overview of irrigation methods used in Florida. Factors affecting irrigation efficiency and uniformity such as design and maintenance are discussed. A wide range of soil moisture sensors (e.g., tensiometers, granular matrix, and capacitance) are currently being used in the state for soil moisture monitoring. Current examples of scheduling tools and automated control systems being used on selected crops in Florida are provided. Research data on the effect of irrigation scheduling and fertigation on nutrient movement, particularly nitrate, are reviewed. Concluding this review is a discussion of potential for adoption of irrigation scheduling and control systems for vegetable crops by Florida growers and future research priorities.

scholarly journals Water Footprint of main crops in Austria / Wasser-Fußabdruck wichtiger Nutzpflanzen in Österreich

2017 ◽  
Vol 68 (1) ◽  
pp. 1-15 ◽  
Author(s):  
Sabina Thaler ◽  
Anne Gobin ◽  
Josef Eitzinger
Keyword(s):  
Crop Yield ◽  
Crop Production ◽  
Agricultural Sector ◽  
Water Footprint ◽  
Irrigation Scheduling ◽  
Yield Potential ◽  
Soil Conditions ◽  
Human Consumption ◽  
Limiting Factor ◽  
The Impact

Summary Water is a key resource for human activities and a critical trigger for the welfare of the whole society. The agricultural sector makes up the main share in global freshwater consumption and is therefore responsible for a large part of the water scarcity in many drought prone regions. As an indicator that relates human consumption to global water resources, the “Water Footprint” (WF) concept can be used, where in case of crop production the total consumed water of crop fields for the crop growing seasons is related to the harvested dry matter crop yield (such as grains). In our study, we simulated the green and primary blue WF of selected main crops for Austrian conditions. Different irrigation scheduling scenarios, demonstrated for a main agricultural production area and various crops in Austria with significant irrigation acreage, were studied. The impact of climate and soil conditions on the green crop WFs of reference crops over the whole territory of Austria were simulated in a second step. Sunflower, winter wheat and grain maize showed the highest WF in the semi-arid study regions, especially on soils with low water capacity. In more humid regions, low temperatures were the main limiting factor on the crop yield potential and frequently led to higher WFs due to lower yields.

scholarly journals Simulation and Prediction of Rainfall and Crop Yield in West Java Using ANFIS

2017 ◽  
Vol 13 (2) ◽  
pp. 83
Author(s):  
Ruminta Roem ◽  
Tati Nurmala
Keyword(s):  
Artificial Intelligence ◽  
Quantitative Analysis ◽  
Crop Yield ◽  
Agricultural Production ◽  
Alternative Model ◽  
Crop Production ◽  
Numerical Data ◽  
West Java ◽  
Study Results ◽  
The Future

Simulation of numerical data for prediction purposes is very important for the planning and anticipation of the future, for example, prediction data of rainfall and agricultural production. There are various models to simulate and forecast the numerical data, one of which is a artificial intelligence model using ANFIS. In this connection it has studied a simulation and prediction of rainfall and agricultural production in West Java using ANFIS. The study uses data of rainfall and crop production. The method of this study is descriptive explanatory which is a type of quantitative analysis. Numerical data were analyzed using ANFIS of the Software Matlab 8.0. The study results showed that ANFIS can simulate rainfall and crop yield with highly accurate and has the potential to be used as one of the alternative model to predict rainfall and crop yield in West Java

scholarly journals Simulation and Prediction of Rainfall and Crop Yield in West Java Using ANFIS

2017 ◽  
Vol 13 (2) ◽  
pp. 83
Author(s):  
Ruminta Roem ◽  
Tati Nurmala
Keyword(s):  
Artificial Intelligence ◽  
Quantitative Analysis ◽  
Crop Yield ◽  
Agricultural Production ◽  
Alternative Model ◽  
Crop Production ◽  
Numerical Data ◽  
West Java ◽  
Study Results ◽  
The Future

Simulation of numerical data for prediction purposes is very important for the planning and anticipation of the future, for example, prediction data of rainfall and agricultural production. There are various models to simulate and forecast the numerical data, one of which is a artificial intelligence model using ANFIS. In this connection it has studied a simulation and prediction of rainfall and agricultural production in West Java using ANFIS. The study uses data of rainfall and crop production. The method of this study is descriptive explanatory which is a type of quantitative analysis. Numerical data were analyzed using ANFIS of the Software Matlab 8.0. The study results showed that ANFIS can simulate rainfall and crop yield with highly accurate and has the potential to be used as one of the alternative model to predict rainfall and crop yield in West Java

Analysis of Crop Yield Prediction of Kharif & Rabi Jowar Crops Using Data Mining Techniques

2017 ◽  
Vol 7 (11) ◽  
pp. 79
Author(s):  
Sujata Mulik
Keyword(s):  
Data Mining ◽  
Crop Yield ◽  
Crop Production ◽  
Climatic Factors ◽  
Crop Productivity ◽  
Yield Prediction ◽  
Data Mining Techniques ◽  
Agriculture Sector ◽  
Using Data ◽  
Rabi Crops

Agriculture sector in India is facing rigorous problem to maximize crop productivity. More than 60 percent of the crop still depends on climatic factors like rainfall, temperature, humidity. This paper discusses the use of various Data Mining applications in agriculture sector. Data Mining is used to solve various problems in agriculture sector. It can be used it to solve yield prediction.  The problem of yield prediction is a major problem that remains to be solved based on available data. Data mining techniques are the better choices for this purpose. Different Data Mining techniques are used and evaluated in agriculture for estimating the future year's crop production. In this paper we have focused on predicting crop yield productivity of kharif & Rabi Crops. 

Sign in / Sign up

Export Citation Format

Share Document