Prediction of organic potato yield using tillage systems and soil properties by artificial neural network (ANN) and multiple linear regressions (MLR)

Abrougui, Khaoula; Gabsi, Karim; Mercatoris, Benoît; Khemis, Chiheb; Amami, Roua; Chehaibi, Sayed

doi:10.1016/j.still.2019.01.011

Cited by 115 publications

(51 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At plot level, the best model for biomass estimation were SMR with H84, PLA, and canopy cover variables, followed by SR, RF, and ANN. The results were consistent with previous studies showing that multiple variable based methods are better than SR methods, and ANN may perform weakly with insufficient sample data [33,34]. However, all the models had R 2 of no more than 0.80, and they all showed a saturation effect.…”

Section: Best Models and Phenotypic Traits For Biomass Estimation At supporting

confidence: 91%

“…ANN, inspired by biological neural networks, is a multilayer fully connected structure for nonlinear feature learning, which consists of an input layer, one or more hidden layers, and an output layer. In this study, the number of hidden layers was set to 1, because one hidden layer is sufficient for solving biomass regressions in most cases [33,34]. In addition to the number of hidden layers, the number of neurons in each layer is also an important parameter.…”

Section: Ann Regression Modelmentioning

confidence: 99%

See 1 more Smart Citation

Non-destructive estimation of field maize biomass using terrestrial lidar: an evaluation from plot level to individual leaf level

Jin

Song

et al. 2020

Plant Methods

View full text Add to dashboard Cite

Background: Precision agriculture is an emerging research field that relies on monitoring and managing field variability in phenotypic traits. An important phenotypic trait is biomass, a comprehensive indicator that can reflect crop yields. However, non-destructive biomass estimation at fine levels is unknown and challenging due to the lack of accurate and high-throughput phenotypic data and algorithms. Results: In this study, we evaluated the capability of terrestrial light detection and ranging (lidar) data in estimating field maize biomass at the plot, individual plant, leaf group, and individual organ (i.e., individual leaf or stem) levels. The terrestrial lidar data of 59 maize plots with more than 1000 maize plants were collected and used to calculate phenotypes through a deep learning-based pipeline, which were then used to predict maize biomass through simple regression (SR), stepwise multiple regression (SMR), artificial neural network (ANN), and random forest (RF). The results showed that terrestrial lidar data were useful for estimating maize biomass at all levels (at each level, R 2 was greater than 0.80), and biomass estimation at leaf group level was the most precise (R 2 = 0.97, RMSE = 2.22 g) among all four levels. All four regression techniques performed similarly at all levels. However, considering the transferability and interpretability of the model itself, SR is the suggested method for estimating maize biomass from terrestrial lidarderived phenotypes. Moreover, height-related variables showed to be the most important and robust variables for predicting maize biomass from terrestrial lidar at all levels, and some two-dimensional variables (e.g., leaf area) and three-dimensional variables (e.g., volume) showed great potential as well. Conclusion: We believe that this study is a unique effort on evaluating the capability of terrestrial lidar on estimating maize biomass at difference levels, and can provide a useful resource for the selection of the phenotypes and models required to estimate maize biomass in precision agriculture practices.

show abstract

Section: Best Models and Phenotypic Traits For Biomass Estimation At supporting

confidence: 91%

Section: Ann Regression Modelmentioning

confidence: 99%

Non-destructive estimation of field maize biomass using terrestrial lidar: an evaluation from plot level to individual leaf level

Jin

Song

et al. 2020

Plant Methods

View full text Add to dashboard Cite

show abstract

“…The relationship between potato yield change and a single climatic factor was calculated by Pearson's correlation analysis [31]. Multiple linear regression was used to quantify the comprehensive relationship between potato yield variation and multiple climatic factors [32]. Statistical analyses were performed using SPSS statistical software (Version 20.0 for Windows, SPSS, USA) [33], and figures were drawn with SigmaPlot (Version 10.0 for Windows, Systat Software) [34].…”

Section: Discussionmentioning

confidence: 99%

Impacts of Recent Climate Change on Potato Yields at a Provincial Scale in Northwest China

Zhang

2020

Agronomy

View full text Add to dashboard Cite

Understanding the effects of climate change on potato yield is vital for food security in northwest China. Based on the long-term data of yields and meteorology, this study analysed the impacts of recent climate change on potato yields at a provincial scale in northwest China. The first difference method was used to disentangle the contributions of climate change from the changes in potato yield in two consecutive years. The moving average method was used to decouple the climate-induced yield of potato. The results showed that the yield and planting area of potato from the period 1982 to 2015 increased markedly, with inter-annual fluctuations. The temperature increased significantly during the potato growing period in northwest China, while other climatic factors did not change significantly. Specifically, the changing trends in climatic factors varied among different provinces. The key meteorological factors limiting potato yield were temperature, precipitation and diurnal temperature range, varying in the different provinces. Potato yields in Gansu, Shaanxi, Ningxia and Xinjiang decreased by 127, 289, 199 and 339 kg ha−1, respectively, for every 1 °C increase in daily maximum temperature. The potato yield in Xinjiang decreased by 583 kg ha−1 for every 1 °C increase in daily minimum temperature. For every 100 mm increase in precipitation, the potato yields in Gansu, Qinghai and Ningxia increased by 250, 375 and 182 kg ha−1, respectively. Combining the first difference method and the moving average method, precipitation was the dominant climatic factor affecting potato yield in rain-fed areas (Gansu, Qinghai and Ningxia). For areas with irrigation (Xinjiang) or relatively high rainfall (Shaanxi), maximum temperature was the deciding climatic factor affecting potato yield. Appropriate adaptation to climate change in the different regions will help to ensure potato production in northwest China.

show abstract

“…Besides, artificial neural network (ANN) was also considered as an alternative model. Traditional ANN, the multilayer perceptron model, has been applied successfully to crop yield estimation with various types of crops [18,19,20].…”

Section: Introductionmentioning

confidence: 99%

County-Level Soybean Yield Prediction Using Deep CNN-LSTM Model

Sun

et al. 2019

Sensors

202

View full text Add to dashboard Cite

Yield prediction is of great significance for yield mapping, crop market planning, crop insurance, and harvest management. Remote sensing is becoming increasingly important in crop yield prediction. Based on remote sensing data, great progress has been made in this field by using machine learning, especially the Deep Learning (DL) method, including Convolutional Neural Network (CNN) or Long Short-Term Memory (LSTM). Recent experiments in this area suggested that CNN can explore more spatial features and LSTM has the ability to reveal phenological characteristics, which both play an important role in crop yield prediction. However, very few experiments combining these two models for crop yield prediction have been reported. In this paper, we propose a deep CNN-LSTM model for both end-of-season and in-season soybean yield prediction in CONUS at the county-level. The model was trained by crop growth variables and environment variables, which include weather data, MODIS Land Surface Temperature (LST) data, and MODIS Surface Reflectance (SR) data; historical soybean yield data were employed as labels. Based on the Google Earth Engine (GEE), all these training data were combined and transformed into histogram-based tensors for deep learning. The results of the experiment indicate that the prediction performance of the proposed CNN-LSTM model can outperform the pure CNN or LSTM model in both end-of-season and in-season. The proposed method shows great potential in improving the accuracy of yield prediction for other crops like corn, wheat, and potatoes at fine scales in the future.

show abstract

Prediction of organic potato yield using tillage systems and soil properties by artificial neural network (ANN) and multiple linear regressions (MLR)

Cited by 115 publications

References 15 publications

Non-destructive estimation of field maize biomass using terrestrial lidar: an evaluation from plot level to individual leaf level

Non-destructive estimation of field maize biomass using terrestrial lidar: an evaluation from plot level to individual leaf level

Impacts of Recent Climate Change on Potato Yields at a Provincial Scale in Northwest China

County-Level Soybean Yield Prediction Using Deep CNN-LSTM Model

Contact Info

Product

Resources

About