scholarly journals Predicting Soybean Yield at the Regional Scale Using Remote Sensing and Climatic Data

2020 ◽  
Vol 12 (12) ◽  
pp. 1936 ◽  
Author(s):  
Alexey Stepanov ◽  
Konstantin Dubrovin ◽  
Aleksei Sorokin ◽  
Tatiana Aseeva
Keyword(s):  
Remote Sensing ◽  
Regression Model ◽  
Crop Yield ◽  
Russian Far East ◽  
Regional Scale ◽  
Arable Land ◽  
Percentage Error ◽  
Climatic Data ◽  
Soybean Yield ◽  
Absolute Percentage Error

Crop yield modeling at the regional level is one of the most important methods to ensure the profitability of the agro-industrial economy and the solving of the food security problem. Due to a lack of information about crop distribution over large agricultural areas, as well as the crop separation problem (based on remote sensing data) caused by the similarity of phenological cycles, a question arises regarding the relevance of using data obtained from the arable land mask of the region to predict the yield of individual crops. This study aimed to develop a regression model for soybean crop yield monitoring in municipalities and was conducted in the Khabarovsk Territory, located in the Russian Far East. Moderate Resolution Imaging Spectroradiometer (MODIS) data, an arable land mask, the meteorological characteristics obtained using the VEGA-Science web service, and crop yield data for 2010–2019 were used. The structure of crop distribution in the Khabarovsk District was reproduced in experimental fields, and Normalized Difference Vegetation Index (NDVI) seasonal variation approximating functions were constructed (both for total district sown area and different crops). It was found that the approximating function graph for the experimental fields corresponds to a similar graph for arable land. The maximum NDVI forecast error on the 30th week in 2019 using the approximation parameters according to 2014–2018 did not exceed 0.5%. The root-mean-square error (RMSE) was 0.054. The maximum value of the NDVI, as well as the indicators characterizing the temperature regime, soil moisture, and photosynthetically active radiation in the region during the period from the 1st to the 30th calendar weeks of the year, were previously considered as parameters of the regression model for predicting soybean yield. As a result of the experiments, the NDVI and the duration of the growing season were included in the regression model as independent variables. According to 2010–2018, the mean absolute percentage error (MAPE) of the regression model was 6.2%, and the soybean yield prediction absolute percentage error (APE) for 2019 was 6.3%, while RMSE was 0.13 t/ha. This approach was evaluated with a leave-one-year-out cross-validation procedure. When the calculated maximum NDVI value was used in the regression equation for early forecasting, MAPE in the 28th–30th weeks was less than 10%.

scholarly journals The influence of climatic characteristics and values of NDVI at soybean yield (on the example of the districts of the Primorskiy region)

2020 ◽  
Vol 192 (1) ◽  
pp. 10-19 ◽  
Author(s):  
Aleksey Stepanov ◽  
Tat’yana Aseyeva ◽  
Konstantin Dubrovin
Keyword(s):  
Regression Model ◽  
Vegetation Index ◽  
Russian Far East ◽  
Far East ◽  
Soil Layer ◽  
Multiple Regression Model ◽  
Percentage Error ◽  
Science System ◽  
Soybean Yield ◽  
Soybean Production

Abstract. The relevance of research. Soybean is one of the key crops in world agriculture; in recent years, soybean production has been actively developing in the Russian Far East. It is necessary to predict yield to solve problems associated with soybean production, including the planning of sown areas and export operations. The purpose of this study is: to determine the factors affecting yield, to establish the relationship between these indicators and yield, and to evaluate the accuracy of the model. Research methods. We examined climatic features and remote Earth sensing indicators of Khankayskiy, Khorol’skiy, Mikhailovskiy and Oktyabr’skiy districts of the Primorskiy region since 2008 to 2018. Meteorological characteristics of territories and values of vegetation index were obtained using the Vega Science system. Integral coefficients were additionally calculated and mutually correlating indicators were excluded from the regression model. The main result of the study is a multiple regression model, where yield is considered as a dependent variable, and the independent variables are: the maximum weekly NDVI, hydrothermal coefficient, duration of the growing season, average annual humidity, and aggregated temperature of the upper soil layer. Mean absolute percentage error of the model is 11.0 % for the Khankayskiy district, 4.8 % for the Khorol’skiy district, 9.5 % for the Oktyabr’skiy district, and 8.9 % for the Mikhailovskiy district. Scientific novelty and practical relevance. A regression model, which predict soybean yield, was developed. In general, the proposed model can be used to predict soybean yield, as well as to make managerial decisions at the regional level.

Regional characterisation of soil properties by combining soil science and hyperspectral and thermal remote sensing: A technical overview of lab and field remote sensing methods

2021 ◽  
Author(s):  
Richard Mommertz ◽  
Lars Konen ◽  
Martin Schodlok
Keyword(s):  
Remote Sensing ◽  
Soil Properties ◽  
Regional Scale ◽  
Arable Land ◽  
Soil Mapping ◽  
Soil Science ◽  
Near Surface ◽  
Soil Parameter ◽  
The Impact ◽  
Parameter Retrieval

<p>Soil is one of the world’s most important natural resources for human livelihood as it provides food and clean water. Therefore, its preservation is of huge importance. For this purpose, a proficient regional database on soil properties is needed. The project “ReCharBo” (Regional Characterisation of Soil Properties) has the objective to combine remote sensing, geophysical and pedological methods to determine soil characteristics on a regional scale. Its aim is to characterise soils non-invasive, time and cost efficient and with a minimal number of soil samples to calibrate the measurements. Konen et al. (2021) give detailed information on the research concept and first field results in a presentation in the session “SSS10.3 Digital Soil Mapping and Assessment”. Hyperspectral remote sensing is a powerful and well known technique to characterise near surface soil properties. Depending on the sensor technology and the data quality, a wide variety of soil properties can be derived with remotely sensed data (Chabrillat et al. 2019, Stenberg et al. 2010). The project aims to investigate the effects of up and downscaling, namely which detail of information is preserved on a regional scale and how a change in scales affects the analysis algorithms and the possibility to retrieve valid soil parameter information. Thus, e.g. laboratory and field spectroscopy are applied to gain information of samples and fieldspots, respectively. Various UAV-based sensors, e.g. thermal & hyperspectral sensors, are applied to study soil properties of arable land in different study areas at field scale. Finally, airborne (helicopter) hyperspectral data will cover the regional scale. Additionally forthcoming spaceborne hyperspectral satellite data (e.g. Prisma, EnMAP, Sentinel-CHIME) are a promising outlook to gain detailed regional soil information. In this context it will be discussed how the multisensor data acquisition is best managed to optimise soil parameter retrieval. Sensor specific properties regarding time and date of acquisition as well as weather/atmospheric conditions are outlined. The presentation addresses and discusses the impact of a multisensor and multiscale remote sensing data collection regarding the results on soil parameter retrieval.</p><p> </p><p>References</p><p>Chabrillat, S., Ben-Dor, E. Cierniewski, J., Gomez, C., Schmid, T. & van Wesemael, B. (2019): Imaging Spectroscopy for Soil Mapping and Monitoring. Surveys in Geophysics 40:361–399. https://doi.org/10.1007/s10712-019-09524-0</p><p>Stenberg, B., Viscarra Rossel, R. A., Mounem Mouazen, A. & Wetterlind, J. (2010): Visible and Near Infrared Spectroscopy in Soil Science. In: Donald L. Sparks (editor): Advances in Agronomy. Vol. 107. Academic Press:163-215. http://dx.doi.org/10.1016/S0065-2113(10)07005-7</p>

scholarly journals An interaction regression model for crop yield prediction

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Javad Ansarifar ◽  
Lizhi Wang ◽  
Sotirios V. Archontoulis
Keyword(s):  
Machine Learning ◽  
Regression Model ◽  
Crop Yield ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Yield Prediction ◽  
Soybean Yield ◽  
Global Food Security ◽  
Management Scenario ◽  
Complex Interactions

AbstractCrop yield prediction is crucial for global food security yet notoriously challenging due to multitudinous factors that jointly determine the yield, including genotype, environment, management, and their complex interactions. Integrating the power of optimization, machine learning, and agronomic insight, we present a new predictive model (referred to as the interaction regression model) for crop yield prediction, which has three salient properties. First, it achieved a relative root mean square error of 8% or less in three Midwest states (Illinois, Indiana, and Iowa) in the US for both corn and soybean yield prediction, outperforming state-of-the-art machine learning algorithms. Second, it identified about a dozen environment by management interactions for corn and soybean yield, some of which are consistent with conventional agronomic knowledge whereas some others interactions require additional analysis or experiment to prove or disprove. Third, it quantitatively dissected crop yield into contributions from weather, soil, management, and their interactions, allowing agronomists to pinpoint the factors that favorably or unfavorably affect the yield of a given location under a given weather and management scenario. The most significant contribution of the new prediction model is its capability to produce accurate prediction and explainable insights simultaneously. This was achieved by training the algorithm to select features and interactions that are spatially and temporally robust to balance prediction accuracy for the training data and generalizability to the test data.

scholarly journals Selection of Independent Variables for Crop Yield Prediction Using Artificial Neural Network Models with Remote Sensing Data

Land ◽  
2021 ◽  
Vol 10 (6) ◽  
pp. 609
Author(s):  
Patryk Hara ◽  
Magdalena Piekutowska ◽  
Gniewko Niedbała
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Crop Yield ◽  
Climatic Data ◽  
Yield Prediction ◽  
Agricultural Crop ◽  
Independent Variables ◽  
Artificial Neural ◽  
Selection Of

Knowing the expected crop yield in the current growing season provides valuable information for farmers, policy makers, and food processing plants. One of the main benefits of using reliable forecasting tools is generating more income from grown crops. Information on the amount of crop yielding before harvesting helps to guide the adoption of an appropriate strategy for managing agricultural products. The difficulty in creating forecasting models is related to the appropriate selection of independent variables. Their proper selection requires a perfect knowledge of the research object. The following article presents and discusses the most commonly used independent variables in agricultural crop yield prediction modeling based on artificial neural networks (ANNs). Particular attention is paid to environmental variables, such as climatic data, air temperature, total precipitation, insolation, and soil parameters. The possibility of using plant productivity indices and vegetation indices, which are valuable predictors obtained due to the application of remote sensing techniques, are analyzed in detail. The paper emphasizes that the increasingly common use of remote sensing and photogrammetric tools enables the development of precision agriculture. In addition, some limitations in the application of certain input variables are specified, as well as further possibilities for the development of non-linear modeling, using artificial neural networks as a tool supporting the practical use of and improvement in precision farming techniques.

scholarly journals Target food security: assimilating ultra-high resolution satellite images into a crop-yield forecasting model

2021 ◽  
Author(s):  
Matteo G. Ziliani ◽  
Bruno Aragon ◽  
Trenton Franz ◽  
Ibrahim Hoteit ◽  
Justin Sheffield ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Crop Yield ◽  
Precision Agriculture ◽  
Satellite Images ◽  
Regional Scale ◽  
Area Index ◽  
High Resolution Satellite Images ◽  
Yield Forecasting ◽  
Crop Yield Forecasting ◽  
The Impact

<p>Assimilating biophysical metrics from remote sensing platforms into crop-yield forecasting models can increase overall model performance. Recent advances in remote sensing technologies provide an unprecedented resource for Earth observation that has both, spatial and temporal resolutions appropriate for precision agriculture applications. Furthermore, computationally efficient assimilation techniques can integrate these new satellite-derived products into modeling frameworks. To date, such modeling approaches work at the regional scale, with comparatively few studies examining the integration of remote sensing and crop-yield modeling at intra-field resolutions. In this study, we investigate the potential of assimilating daily, 3 m satellite-derived leaf area index (LAI) into the Agricultural Production Systems sIMulator (APSIM) for crop yield estimation in a rainfed corn field located in Nebraska. The impact of the number of satellite images and the definition of homogeneous spatial units required to re-initialize input parameters was also evaluated. Results show that the observed spatial variability of LAI within the maize field can effectively drive the crop simulation model and enhance yield forecasting that takes into account intra-field variability. The detection of intra-field biophysical metrics is particularly valuable since it may be employed to infer inefficiency problems at different stages of the season, and hence drive specific and localized management decisions for improving the final crop yield.</p>

scholarly journals Evaluation Des Risques D’érosion Hydrique Et Cartographie Des Zones Vulnérables Par La Méthode RUSLE Couplée Aux SIG Et À La Télédétection Dans Le Bassin Versant d’Agoudal En Amont De La Vallée d’Imilchil (Haut Atlas Central, Maroc)

2021 ◽  
Vol 17 (21) ◽  
pp. 66
Author(s):  
Youssef ◽  
El-Arbi Ait Yacine ◽  
Brahim Benzougagh ◽  
Laila Nassiri ◽  
Jamal Ibijbijen
Keyword(s):  
Remote Sensing ◽  
Arable Land ◽  
Ecological Factors ◽  
Remote Sensing Data ◽  
Water Erosion ◽  
Climatic Data ◽  
Degradation Rates ◽  
Systèmes D’Information ◽  
Specific Degradation ◽  
Bassin Versant

Le sous-bassin versant (SBV) d’Agoudal est la partie amont de la vallée d’Imilchil relevant de la province de Midelt et la région de Draa-Tafilalet au Sud-Est du Maroc. Il s’étale sur la tranche altitudinale asylvatique du Haut Atlas central, allant de 2400 à plus de 3150 m. Ce sont des écosystèmes fragiles dont les sols sont peu arables et peu protégés, à haut risques d’érosion. Ils sont dans un stade très avancé de dégradation, sous l’effet de l’action de l’Homme, des facteurs écologiques, aggravés par les changements climatiques. L’objectif principal de cette recherche est d’évaluer le degré de sensibilité de la zone d’étude vis-à-vis de l’érosion hydrique et de cartographier les zones vulnérables prioritaires pour d’éventuelles interventions d’atténuation. La méthode utilisée s’est basée sur l’Équation Universelle Révisée des Pertes en sols (RUSLE) en intégrant les différents facteurs causaux de ladite équation dans le Systèmes d’Information Géographique (SIG) et en se servant des données officielles (cartes géologiques et topographiques de la zone d’études, données climatiques, les études sur l’érosion réalisées par les départements étatiques concernés) et la télédétection, validées par les réalités de terrain. Les résultats dégagés montrent que la quasi-totalité de ce bassin est soumis à une forte dégradation des sols ; en effet près de 66% de la superficie de la zone d’étude est couverte par les classes de dégradation spécifique de 50 à 400 t/ha/an et 18.9% affiche des taux faibles à moyens allant de 7,4 à 32,17 t/ha/an. Seulement 1,4% du SVB est soumise à des taux de dégradation spécifique inférieurs à 7,4 t/ha/an. La valeur moyenne du taux d’érosion est de 255t/h/an, avec un écart type de près 285 t/an/ha, dû l’hétérogénéité des caractéristiques du milieu et de ses conditions. Ces chiffres attestent que cette région est soumise aux hauts risques d’érosion. Ce phénomène ajouté aux inondations récurrentes, constituent la principale menace qui met en péril l’agriculture vivrière de cette zone, ce qui donne le signal d’alarme pour intervention de mitigation urgente. The Agoudal sub-basin is the upstream part of the Assif Melloul watershed in the Imilchil valley belonging to the province of Midelt and the region of Draa-Tafilalet in south-eastern Morocco. It is located on the Asylvatic altitudinal slice of the Central High Atlas, ranging from 2400 to more than 3150 m. These are fragile ecosystems with poor arable land that are poorly protected, with a high risk of erosion. They are in fact in their advanced stage of degradation due to human activities and ecological factors aggravated by climate change. This paper focuses on assessing the degree of sensitivity of this area to water erosion, and it aims to map priority vulnerable areas for any future mitigation intervention. The method was based on the Revised Universal Soil Loss Equation (RUSLE) by integrating the causal factors of this equation in Geographic Information Systems (GIS) and by using remote sensing data validated based on official data (geological maps and topography of the study area, climatic data, studies on erosion carried out by the state departments concerned) and remote sensing (validated by the realities on the ground). The results show that almost all the watershed is subject to severe soil degradation due to water erosion. In fact, nearly 66% of its area is covered by specific degradation classes of 50 to 400 t / ha / year, and 18.9% of the area displays low and medium erosion rates. Only 1.4% of the study area is subject to specific degradation rates less than 7.4 t / ha / year. The average erosion rate is 255 t / h / year, with a standard deviation of 285 t / year / ha, mainly due to the heterogeneity of the characteristics and its conditions. These figures show that this region is subject to high risks of erosion. This phenomenon, along with recurrent floods, constitutes the main threat that is endangering subsistence agriculture, which gives the alarm signal for urgent mitigation intervention.

scholarly journals Factors Affecting the Productivity of the Big Onion in Hambantota District during the Off Season

2019 ◽  
pp. 1-10
Author(s):  
M. K. M. Sulochana ◽  
L. S. Nawarathna
Keyword(s):  
Linear Regression ◽  
Regression Model ◽  
Multiple Linear Regression ◽  
Linear Regression Model ◽  
Multiple Linear Regression Model ◽  
Mean Absolute Percentage Error ◽  
Percentage Error ◽  
Factors Affecting ◽  
Absolute Percentage Error ◽  
Average Productivity

Aim: The main aim of this study is to identify the factors affecting the big onion productivity of Hambantota district during the off-season. Moreover, we identify the average productivity per acre from Hambantota district and compare it with the other areas that cultivated the big onion. Further, identify the main issues encountered in big onion cultivation in Hambantota and identify the critical contributing factors for the big onion cultivation in this area. Place and Duration of Study: During the off seasons in 2015 to 2016 in Hambantota District. Methodology: Sample data was collected from 201 farmers in Hambantota district. Multiple linear regression model was used to identify the factors affecting the big onion productivity in Hambantota district during the off-season. The normality assumption of the regression model was checked using Kolmogorov–Smirnov test, Shapiro Wilk normality test and Skewness and Kurtosis test. Pearson, Spearman’s Rank and Partial correlation tests were used to check the correlations between variables. Mean absolute percentage error (MAPE) and Symmetrical Mean absolute percentage error (SMAPE) values were used to validate the fitted model. Results: By the multiple linear regression model main factors affecting the productivity of big onion in Hambantota area were Seasonal Months, Monthly Income, Subsidies Fertilizer and Cultivated Quantity. And the R-squared value was most like to 80% and this means these independent variables were described 80% of the dependent variable.  Model accuracies were reported as 98.48% and 98.49% from MAPE and SMAPE respectively. Therefore, this multiple linear regression model was suitable for this study. Further, the model determined the affected factors for the big onion cultivation in Hambantota district during the off-season. Conclusion: Hambantota district average productivity was less than other areas. Big onion productivity of Matale is more than 2 times greater than big onion productivity of Hambantota. Off season big onion cultivation in Hambantota district is not very effective because of the average productivity is less than other areas in Sri Lanka.

scholarly journals Remote Sensing-Based Quantification of the Summer Maize Yield Gap Induced by Suboptimum Sowing Dates over North China Plain

2021 ◽  
Vol 13 (18) ◽  
pp. 3582 ◽  
Author(s):  
Sha Zhang ◽  
Yun Bai ◽  
Jiahua Zhang
Keyword(s):  
Remote Sensing ◽  
Crop Yield ◽  
North China Plain ◽  
North China ◽  
Regional Scale ◽  
Maize Yield ◽  
Yield Potential ◽  
Management Information ◽  
Summer Maize ◽  
Yield Gap

Estimating yield potential (Yp) and quantifying the contribution of suboptimum field managements to the yield gap (Yg) of crops are important for improving crop yield effectively. However, achieving this goal on a regional scale remains difficult because of challenges in collecting field management information. In this study, we retrieved crop management information (i.e., emerging stage information and a surrogate of sowing date (SDT)) from a remote sensing (RS) vegetation index time series. Then, we developed a new approach to quantify maize Yp, total Yg, and the suboptimum SDT-induced Yg (Yg0) using a process-based RS-driven crop yield model for maize (PRYM–Maize), which was developed in our previous study. PRYM–Maize and the newly developed method were used over the North China Plain (NCP) to estimate Ya, Yp, Yg, and Yg0 of summer maize. Results showed that PRYM–Maize outputs reasonable estimates for maize yield over the NCP, with correlations and root mean standard deviation of 0.49 ± 0.24 and 0.88 ± 0.14 t hm−2, respectively, for modeled annual maize yields versus the reference value for each year over the period 2010 to 2015 on a city level. Yp estimated using our new method can reasonably capture the spatial variations in site-level estimates from crop growth models in previous literature. The mean annual regional Yp of 2010–2015 was estimated to be 11.99 t hm−2, and a Yg value of 5.4 t hm−2 was found between Yp and Ya on a regional scale. An estimated 29–42% of regional Yg in each year (2010–2015) was induced by suboptimum SDT. Results also show that not all Yg0 was persistent over time. Future studies using high spatial-resolution RS images to disaggregate Yg0 into persistent and non-persistent components on a small scale are required to increase maize yield over the NCP.

Sign in / Sign up

Export Citation Format

Share Document