Big Data and Machine Learning With Hyperspectral Information in Agriculture

Kenneth Li-Minn Ang,Jasmine Kah Phooi Seng

doi:10.1109/access.2021.3051196

Kenneth Li-Minn Ang, Jasmine Kah Phooi Seng

Open Access

https://doi.org/10.1109/access.2021.3051196

Copy DOI

Abstract

Hyperspectral and multispectral information processing systems and technologies have demonstrated its usefulness for the improvement of agricultural productivity and practices by providing useful information to farmers and crop managers on the factors affecting crop status and growth. These technologies are widely used in a range of agriculture applications such as crop management, crop yield forecasting, crop disease detection, and the monitoring of agriculture land usage, water, and soil conditions. Hyperspectral information sensing can acquire several hundred spectral bands that cover the electromagnetic spectrum of an observational scene in a single acquisition. The resulting hyperspectral data cube contains a large volume of spatial and spectral information. The hyperspectral sequence of images or video further increases the data generation velocity and volume which lead to the Big data challenges particularly in agricultural remote sensing applications. This paper is structured to first give a comprehensive review of representative studies to provide insights into significant research efforts in agriculture using Big data, machine learning and deep learning with the focus on frameworks or architectures, information processing and analytics with hyperspectral and multispectral data. The potential for utilizing Big data, machine learning and deep learning for hyperspectral and multispectral data in agriculture is very promising. The paper then further explores the potential of using ensemble machine learning and scalable parallel discriminant analysis which takes into consideration the spatial and spectral components for Big data in agriculture. To the best of our knowledge, no similar review study on agriculture with Big data, machine learning and deep learning for hyperspectral and multispectral information processing has been reported. Furthermore, the potential of ensemble machine learning and scalable parallel discriminant analysis has not been explored in agriculture information processing. Experiments and data analytics have been performed on hyperspectral data from agriculture for validation. The results have shown the good performance of our approach.

Highlights

The authors in [1] project that an increase of approximately 25% to 70% above current production levels may be needed to meet the global crop demand in 2050
Their work was implemented by TensorFlow and the results showed good performance and that the estimated yield of winter wheat based on time-series remote sensing images was highly correlated with statistical data (Pearson r value of 0.82), and demonstrated that the Convolutional Neural Networks (CNNs) could provide a useful reference for estimating crop yield
There are several challenges which need to be further addressed to achieve the potential of Big data and hyperspectral information processing in agriculture: (1) The need for efficient machine learning algorithms and classifiers, and to overcome the shortage of high-quality and labeled training images; (2) The need for efficient and scalable computational architectures for efficient information processing; (3) The need for standardization and ease of use for different remote sensing formats and sensor resolutions for non-expert users; and (4) The need for data management systems to support the efficient storing and indexing of geographical metadata

Summary

Introduction

The authors in [1] project that an increase of approximately 25% to 70% above current production levels may be needed to meet the global crop demand in 2050. Big data provides farmers with useful and actionable information on weather and seasonal patterns, rain and water cycles, fertilizer requirements, and other critical information for harvesting and decisionmaking. This enables farmers, agricultural suppliers and other stakeholders to make smart decisions such as the cycles for crops planting to increase profitability and the planning of optimal harvesting times leading to improved farm yields. The authors in [2]

Methods

Results

Conclusion