Short term soil moisture forecasts for potato crop farming: A machine learning approach

Dubois, Amaury; Teytaud, Fabien; Vérel, Sebástien

doi:10.1016/j.compag.2020.105902

Cited by 49 publications

(21 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The models’ output was the estimated soil matric potential at 0.20 m depth, where thresholds can be used in practice to trigger irrigation events. Gumiere et al (2020) and Dubois et al (2021) also explored machine learning models for predicting soil matric potential in cranberry and potato crops, respectively, for irrigation management. In Gumiere et al (2020) , a Random Forest (RF) model with rainfall, reference evapotranspiration and soil matric potential measurements at 0.10 m as input data predicted hourly soil matric potential with an R 2 of 0.58.…”

Section: Discussionmentioning

confidence: 99%

Machine learning approach to estimate soil matric potential in the plant root zone based on remote sensing data

2022

View full text Add to dashboard Cite

There is an increasing interest in using the Internet of Things (IoT) in the agriculture sector to acquire soil- and crop-related parameters that provide helpful information to manage farms more efficiently. One example of this technology is using IoT soil moisture sensors for scheduling irrigation. Soil moisture sensors are usually deployed in nodes. A more significant number of sensors/nodes is recommended in larger fields, such as those found in broadacre agriculture, to better account for soil heterogeneity. However, this comes at a higher and often limiting cost for farmers (purchase, labour costs from installation and removal, and maintenance). Methodologies that enable maintaining the monitoring capability/intensity with a reduced number of in-field sensors would be valuable for the sector and of great interest. In this study, sensor data analysis conducted across two irrigation seasons in three cotton fields from two cotton-growing areas of Australia, identified a relationship between soil matric potential and cumulative satellite-derived crop evapotranspiration (ETcn) between irrigation events. A second-degree function represents this relationship, which is affected by the crop development stage, rainfall, irrigation events and the transition between saturated and non-saturated soil. Two machine learning models [a Dense Multilayer Perceptron (DMP) and Support Vector Regression (SVR) algorithms] were studied to explore these second-degree function properties and assess whether the models were capable of learning the pattern of the soil matric potential-ETcn relation to estimate soil moisture from satellite-derived ETc measurements. The algorithms performance evaluation in predicting soil matric potential applied the k-fold method in each farm individually and combining data from all fields and seasons. The latter approach made it possible to avoid the influence of farm consultants’ decisions regarding when to irrigate the crop in the training process. Both algorithms accurately estimated soil matric potential for individual (up to 90% of predicted values within ±10 kPa) and combined datasets (73% of predicted values within ±10 kPa). The technique presented here can accurately monitor soil matric potential in the root zone of cotton plants with reduced in-field sensor equipment and offers promising applications for its use in irrigation-decision systems.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine learning approach to estimate soil matric potential in the plant root zone based on remote sensing data

2022

View full text Add to dashboard Cite

show abstract

“…Rahmati et al (2020) revealed that RF had better classification ability than SVM when predicting agricultural droughts in Australia. Dubois et al (2021) reported that RF and SVM had better quantitative prediction ability than ANNs for forecasting soil moisture in the short-term. In other fields, Uddin et al (2019) unveiled that in disease detection, RF had the highest chance to show excellent classification capability (with an AUC over 0.8), followed by SVM, NB, ANNs, KNN.…”

Section: Discussionmentioning

confidence: 99%

Performances of Machine Learning Algorithms in Predicting the Productivity of Conservation Agriculture at a Global Scale

Zhang

Gabrielle

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

Assessing the productive performance of conservation agriculture (CA) has become a major issue due to growing concerns about global food security and sustainability. Numerous experiments have been conducted to assess the performance of CA under various local conditions, and meta-analysis has become a standard approach in agricultural sector for analysing and summarizing the experimental data. Meta-analysis provides valuable synthetic information based on mean effect size estimation. However, summarizing large amounts of information by way of a single mean effect value is not always satisfactory, especially when considering agricultural practices. Indeed, their impacts on crop yields are often non-linear, and vary widely depending on a number of factors, including soil properties and local climate conditions. To address this issue, here we present a machine learning approach to produce data-driven global maps describing the spatial distribution of the productivity of CA versus conventional tillage (CT). Our objective is to evaluate and compare several machine-learning models for their ability in estimating the productivity of CA systems, and to analyse uncertainty in the model outputs. We consider different usages, including classification, point regression and quantile regression. Our approach covers the comparison of 12 different machine learning algorithms, model training, tuning with cross-validation, testing, and global projection of results. The performances of these algorithms are compared based on a recent global dataset including more than 4,000 pairs of crop yield data for CA vs. CT. We show that random forest has the best performance in classification and regression, while quantile regression forest performs better than quantile neural networks in quantile regression. The best algorithms are used to map crop productivity of CA vs. CT at the global scale, and results reveal that the performance of CA vs. CT is characterized by a strong spatial variability, and that the probability of yield gain with CA is highly dependent on geographical locations. This result demonstrates that our approach is much more informative than simply presenting average effect sizes produced by standard meta-analyses, and paves the way for such probabilistic, spatially-explicit approaches in many other fields of research.

show abstract

“…Topic Solution [47] Soil Nutrition [51] Soil Classification [48] Soil Detection System [49] Soil Humidity Sensing [52], [53] Soil Moisture Prediction and Forecast [54] Soil Moisture Evaluation [55], [56] Soil Prediction [57] Soil Estimate Soil Moisture [50] Soil Analysis Kwok and Sun [59], On technology in ML can be used for learning and is very important in agriculture. In recent years, many studies have taken advantage of machine learning as part of AI.…”

Section: Referencesmentioning

confidence: 99%

A Systematic Review of Current Trends in Artificial Intelligence for Smart Farming to Enhance Crop Yield

Widianto

Ardimansyah²,

Pohan³

et al. 2022

Journal of Robotics and Control

View full text Add to dashboard Cite

Current technology has been widely applied for development, one of which has an Artificial Intelligence (AI) applied to Smart Farming. AI can give special capabilities to be programmed as needed. In cooperation with agricultural systems, AI is part of improving the quality of agriculture. This technology is no stranger to being applied in basic fields such as agriculture. This smart technology is needed to increase crop yields for various regions by utilizing the current trends paper. This is necessary because less land is available for agriculture, and there is a greater need for food sources. Therefore, this systematic review aims to collect the current trends in AI studies for Smart Farming papers using the latest year features from 2018-2022. This paper is handy for researchers and industry in looking for the latest papers on research to enhance crop yields. The authors utilized Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) of 534 articles from IEEE, ACM, MDPI, IAES, and ScienceDirect. After going through a careful process, 67 papers were found that were judged according to the criteria. After the authors got some of the current trends, the author has discussed several factors regarding the results obtained to enhance crop yields, such as Weather, Soil, Irrigation, Unmanned Aerial Vehicle (UAV), Pest Control, Weed Control, and Disease Control.

show abstract

Short term soil moisture forecasts for potato crop farming: A machine learning approach

Cited by 49 publications

References 39 publications

Machine learning approach to estimate soil matric potential in the plant root zone based on remote sensing data

Machine learning approach to estimate soil matric potential in the plant root zone based on remote sensing data

Performances of Machine Learning Algorithms in Predicting the Productivity of Conservation Agriculture at a Global Scale

A Systematic Review of Current Trends in Artificial Intelligence for Smart Farming to Enhance Crop Yield

Contact Info

Product

Resources

About