In India, Agriculture plays an imperative role in the development of our country. More than 50% of entirety populace of India is directly or indirectly depends on agriculture and the agronomist are the backbone of the agronomic diligence but the agricultural backdrop facing decades-long tribulations and unpredicted challenges that are so critical to resolve. Some of the major issues that agronomist finding hard is water scarcity, soil erosion, lack of market intellect, poor quality of seeds, usage of fertilizers, inadequate knowledge on preserving soil for further cultivation etc. In addition to this, due to Covid19, still more problems faced by farmers are shortage of agri-inputs, lack of laborers and transportation of farm products. In order to rectify some of the agricultural tribulations, this paper has been primed as an effort to re-evaluate the study on the significance of deep learning techniques in the domain of agro crop yield production and rainfall-temperature forecasting with respect to density. The objective is to build an application that is user-friendly for the agronomist suggesting legitimate crop selection fine points according to the crop year, zone, season, soil nutrient on their farm which hikes the yield of the crops devoid of fertilizers and preserving the soil composition without degradation as well. This work integrates finding soil nutrients such as Nitrogen, Potassium, and Phosphorous. The input parameters considered for predicting the crop are likely the district, the crop year and the previous crop planted. Based on the survey, Artificial Neural Networks(ANN), Convolutional Neural Network(CNN), Decision Tree, Recurrent Neural Network (RNN), Random Forest and Support Vector Machine(SVM) classification models are the best models to predict accurate values and obtained the optimized results.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Deep Learning in Agronomic Forecast


    Beteiligte:


    Erscheinungsdatum :

    02.12.2021


    Format / Umfang :

    3106864 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    A Deep Machine Learning Algorithm to Optimize the Forecast of Atmospherics

    Russell, Alexandria M. | British Library Conference Proceedings | 2017


    A deep learning and ensemble learning based architecture for metro passenger flow forecast

    Wang, Xin / Zhu, Changfeng / Jiang, Jiahao | Wiley | 2023

    Freier Zugriff

    A deep learning and ensemble learning based architecture for metro passenger flow forecast

    Xin Wang / Changfeng Zhu / Jiahao Jiang | DOAJ | 2023

    Freier Zugriff

    LSTM network: a deep learning approach for short‐term traffic forecast

    Zhao, Zheng / Chen, Weihai / Wu, Xingming et al. | Wiley | 2017

    Freier Zugriff