Submit to Remote Sensing Review for Remote Sensing Propose a Special Issue

Journal Browser

Deep Learning Methods for Crop Monitoring and Crop Yield Prediction

Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Remote Sensing in Agriculture and Vegetation".

Deadline for manuscript submissions: closed (30 April 2021) | Viewed by 30891

Share This Special Issue

Special Issue Editors

Prof. Tarmo Lipping

E-Mail Website
Guest Editor

Computing Sciences Unit, Faculty of Information Technology and Communication Sciences, Tampere University, 28101 Pori, Finland
Interests: data analytics; machine learning; time series analysis; geographic information systems; geospatial data analysis; decision support

Dr. Miao Zhang

E-Mail Website
Guest Editor

Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
Interests: crop monitoring with remote sensing; big earth data for cropland monitoring; agricultural remote sensing
Special Issues, Collections and Topics in MDPI journals

Dr. Nathaniel Narra

E-Mail Website
Guest Editor

Computing Sciences Unit, Faculty of Information Technology and Communication Sciences, Tampere University, 28101 Pori, Finland
Interests: image analysis; deep learning; remote sensing; crop yield; conformal mapping; decision support

Special Issue Information

Remote sensing and statistical methods have been extensively used for crop assessment at regional, national, and global scales, with many studies informing national and regional agricultural policies. The sensing platforms have been largely satellite-based. However, with greater resolutions of sensing equipment and proliferation of UAVs, field scale analyses have become an additional possibility.

Recent advances in data acquisition capabilities, computational platforms (especially utilizing massive parallel processing using high-performance GPU boards), and Big Data structures have enabled the emergence of deep learning architectures, capable of performing tasks previously not feasible using conventional machine learning techniques. Characteristic features of these architectures include relying on extensive heterogenous data sets and learning from raw data rather than requiring separate feature extraction stage.

This Special Issue focuses on the latest research advances in assessing crop development and predicting crop yield throughout the growing season in open fields and greenhouses. With exploding applications of deep learning in agriculture, this Special Issue would like to invite submissions that specifically focus on target detection, qualitative and quantitative metrics for crop condition assessment, and crops yield estimation and prediction from remote sensing using deep learning techniques. Submissions in the form of research articles, reviews, perspectives, and case studies are all welcome. We especially invite studies that promote usability in terms of access to code or developed tools.

Prof. Tarmo Lipping
Dr. Miao Zhang
Dr. Nathaniel Narra
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

yield prediction
crop monitoring
multispectral imaging
smart agriculture
machine learning
deep learning
big data analytics

Published Papers (7 papers)

Download All Papers

Research

14 pages, 2427 KiB

Open AccessArticle

Predicting Maize Yield at the Plot Scale of Different Fertilizer Systems by Multi-Source Data and Machine Learning Methods

by Linghua Meng, Huanjun Liu, Susan L. Ustin and Xinle Zhang

Remote Sens. 2021, 13(18), 3760; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13183760 - 19 Sep 2021

Cited by 17 | Viewed by 3024

Abstract

Timely and reliable maize yield prediction is essential for the agricultural supply chain and food security. Previous studies using either climate or satellite data or both to build empirical or statistical models have prevailed for decades. However, to what extent climate and satellite data can improve yield prediction is still unknown. In addition, fertilizer information may also improve crop yield prediction, especially in regions with different fertilizer systems, such as cover crop, mineral fertilizer, or compost. Machine learning (ML) has been widely and successfully applied in crop yield prediction. Here, we attempted to predict maize yield from 1994 to 2007 at the plot scale by integrating multi-source data, including monthly climate data, satellite data (i.e., vegetation indices (VIs)), fertilizer data, and soil data to explore the accuracy of different inputs to yield prediction. The results show that incorporating all of the datasets using random forests (RF) and AB (adaptive boosting) can achieve better performances in yield prediction (R²: 0.85~0.98). In addition, the combination of VIs, climate data, and soil data (VCS) can predict maize yield more effectively than other combinations (e.g., combinations of all data and combinations of VIs and soil data). Furthermore, we also found that including different fertilizer systems had different prediction accuracies. This paper aggregates data from multiple sources and distinguishes the effects of different fertilization scenarios on crop yield predictions. In addition, the effects of different data on crop yield were analyzed in this study. Our study provides a paradigm that can be used to improve yield predictions for other crops and is an important effort that combines multi-source remotely sensed and environmental data for maize yield prediction at the plot scale and develops timely and robust methods for maize yield prediction grown under different fertilizing systems. Full article

(This article belongs to the Special Issue Deep Learning Methods for Crop Monitoring and Crop Yield Prediction)

► Show Figures

Figure 1

16 pages, 3244 KiB

Open AccessArticle

Cotton Stand Counting from Unmanned Aerial System Imagery Using MobileNet and CenterNet Deep Learning Models

by Zhe Lin and Wenxuan Guo

Remote Sens. 2021, 13(14), 2822; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13142822 - 18 Jul 2021

Cited by 29 | Viewed by 4322 | Correction

Abstract

An accurate stand count is a prerequisite to determining the emergence rate, assessing seedling vigor, and facilitating site-specific management for optimal crop production. Traditional manual counting methods in stand assessment are labor intensive and time consuming for large-scale breeding programs or production field operations. This study aimed to apply two deep learning models, the MobileNet and CenterNet, to detect and count cotton plants at the seedling stage with unmanned aerial system (UAS) images. These models were trained with two datasets containing 400 and 900 images with variations in plant size and soil background brightness. The performance of these models was assessed with two testing datasets of different dimensions, testing dataset 1 with 300 by 400 pixels and testing dataset 2 with 250 by 1200 pixels. The model validation results showed that the mean average precision (mAP) and average recall (AR) were 79% and 73% for the CenterNet model, and 86% and 72% for the MobileNet model with 900 training images. The accuracy of cotton plant detection and counting was higher with testing dataset 1 for both CenterNet and MobileNet models. The results showed that the CenterNet model had a better overall performance for cotton plant detection and counting with 900 training images. The results also indicated that more training images are required when applying object detection models on images with different dimensions from training datasets. The mean absolute percentage error (MAPE), coefficient of determination (R²), and the root mean squared error (RMSE) values of the cotton plant counting were 0.07%, 0.98 and 0.37, respectively, with testing dataset 1 for the CenterNet model with 900 training images. Both MobileNet and CenterNet models have the potential to accurately and timely detect and count cotton plants based on high-resolution UAS images at the seedling stage. This study provides valuable information for selecting the right deep learning tools and the appropriate number of training images for object detection projects in agricultural applications. Full article

(This article belongs to the Special Issue Deep Learning Methods for Crop Monitoring and Crop Yield Prediction)

► Show Figures

Graphical abstract

21 pages, 4172 KiB

Open AccessArticle

Using Hybrid Artificial Intelligence and Evolutionary Optimization Algorithms for Estimating Soybean Yield and Fresh Biomass Using Hyperspectral Vegetation Indices

by Mohsen Yoosefzadeh-Najafabadi, Dan Tulpan and Milad Eskandari

Remote Sens. 2021, 13(13), 2555; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13132555 - 30 Jun 2021

Cited by 45 | Viewed by 4338

Abstract

Recent advanced high-throughput field phenotyping combined with sophisticated big data analysis methods have provided plant breeders with unprecedented tools for a better prediction of important agronomic traits, such as yield and fresh biomass (FBIO), at early growth stages. This study aimed to demonstrate the potential use of 35 selected hyperspectral vegetation indices (HVI), collected at the R5 growth stage, for predicting soybean seed yield and FBIO. Two artificial intelligence algorithms, ensemble-bagging (EB) and deep neural network (DNN), were used to predict soybean seed yield and FBIO using HVI. Considering HVI as input variables, the coefficients of determination (R²) of 0.76 and 0.77 for yield and 0.91 and 0.89 for FBIO were obtained using DNN and EB, respectively. In this study, we also used hybrid DNN-SPEA2 to estimate the optimum HVI values in soybeans with maximized yield and FBIO productions. In addition, to identify the most informative HVI in predicting yield and FBIO, the feature recursive elimination wrapper method was used and the top ranking HVI were determined to be associated with red, 670 nm and near-infrared, 800 nm, regions. Overall, this study introduced hybrid DNN-SPEA2 as a robust mathematical tool for optimizing and using informative HVI for estimating soybean seed yield and FBIO at early growth stages, which can be employed by soybean breeders for discriminating superior genotypes in large breeding populations. Full article

(This article belongs to the Special Issue Deep Learning Methods for Crop Monitoring and Crop Yield Prediction)

► Show Figures

Graphical abstract

24 pages, 6278 KiB

Open AccessArticle

Corn Biomass Estimation by Integrating Remote Sensing and Long-Term Observation Data Based on Machine Learning Techniques

by Liying Geng, Tao Che, Mingguo Ma, Junlei Tan and Haibo Wang

Remote Sens. 2021, 13(12), 2352; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13122352 - 16 Jun 2021

Cited by 28 | Viewed by 3094

Abstract

The accurate and timely estimation of regional crop biomass at different growth stages is of great importance in guiding crop management decision making. The recent availability of long time series of remote sensing data offers opportunities for crop monitoring. In this paper, four machine learning models, namely random forest (RF), support vector machine (SVM), artificial neural network (ANN), and extreme gradient boosting (XGBoost) were adopted to estimate the seasonal corn biomass based on field observation data and moderate resolution imaging spectroradiometer (MODIS) reflectance data from 2012 to 2019 in the middle reaches of the Heihe River basin, China. Nine variables were selected with the forward feature selection approach from among twenty-seven variables potentially influencing corn biomass: soil-adjusted total vegetation index (SATVI), green ratio vegetation index (GRVI), Nadir_B7 (2105–2155 nm), Nadir_B6 (1628–1652 nm), land surface water index (LSWI), normalized difference vegetation index (NDVI), Nadir_B4 (545–565 nm), and Nadir_B3 (459–479 nm). The results indicated that the corn biomass was suitably estimated (the coefficient of determination (R²) was between 0.72 and 0.78) with the four machine learning models. The XGBoost model performed better than the other three models (R² = 0.78, root mean squared error (RMSE) = 2.86 t/ha and mean absolute error (MAE) = 1.86 t/ha). Moreover, the RF model was an effective method (R² = 0.77, RMSE = 2.91 t/ha and MAE = 1.91 t/ha), with a performance comparable to that of the XGBoost model. This study provides a reference for estimating crop biomass from MOD43A4 datasets. In addition, the research demonstrates the potential of machine learning techniques to achieve a relatively accurate estimation of daily corn biomass at a large scale. Full article

(This article belongs to the Special Issue Deep Learning Methods for Crop Monitoring and Crop Yield Prediction)

► Show Figures

Figure 1

25 pages, 4723 KiB

Open AccessArticle

Estimation of Rangeland Production in the Arid Oriental Region (Morocco) Combining Remote Sensing Vegetation and Rainfall Indices: Challenges and Lessons Learned

by Marie Lang, Hamid Mahyou and Bernard Tychon

Remote Sens. 2021, 13(11), 2093; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13112093 - 26 May 2021

Cited by 5 | Viewed by 2834

Abstract

This study aimed at investigating the potential of vegetation indices and precipitation-related variables derived from remote sensing to assess rangeland production in the arid environment of the Moroccan Oriental region and identifying the challenges linked to that particular biome. Vegetation indices (VIs) and the Standardized Precipitation Index (SPI) computed at various aggregation periods were first integrated into a Random Forest model. In a second step, we studied in more detail the linear relationship between rangeland biomass and one of the spectral indices (ARVI) for the various vegetation formations present in the area. We concluded that, mostly due to the presence of alfa steppes (Stipa tenacissima), and especially to a large proportion of non-photosynthetic vegetation, it is not possible to accurately estimate rangeland production with a global model in this region. We recommend separating Stipa tenacissima from the other species in models and focusing on methods aimed at studying dry and non-photosynthetic vegetation to improve the quality of the prediction for alfa steppes. Full article

(This article belongs to the Special Issue Deep Learning Methods for Crop Monitoring and Crop Yield Prediction)

► Show Figures

Graphical abstract

23 pages, 11512 KiB

Open AccessArticle

How Can We Realize Sustainable Development Goals in Rocky Desertified Regions by Enhancing Crop Yield with Reduction of Environmental Risks?

by Boyi Liang, Timothy A. Quine, Hongyan Liu, Elizabeth L. Cressey and Ian Bateman

Remote Sens. 2021, 13(9), 1614; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13091614 - 21 Apr 2021

Cited by 3 | Viewed by 2147

Abstract

To meet the sustainable development goals in rocky desertified regions like Guizhou Province in China, we should maximize the crop yield with minimal environmental costs. In this study, we first calculated the yield gap for 6 main crop species in Guizhou Province and evaluated the quantitative relationships between crop yield and influencing variables utilizing ensembled artificial neural networks. We also tested the influence of adjusting the quantity of local fertilization and irrigation on crop production in Guizhou Province. Results showed that the total yield of the selected crops had, on average, reached over 72.5% of the theoretical maximum yield. Increasing irrigation tended to be more consistently effective at increasing crop yield than additional fertilization. Conversely, appropriate reduction of fertilization may even benefit crop yield in some regions, simultaneously resulting in significantly higher fertilization efficiency with lower residuals in the environment. The total positive impact of continuous intensification of irrigation and fertilization on most crop species was limited. Therefore, local stakeholders are advised to consider other agricultural management measures to improve crop yield in this region. Full article

(This article belongs to the Special Issue Deep Learning Methods for Crop Monitoring and Crop Yield Prediction)

► Show Figures

Graphical abstract

18 pages, 5022 KiB

Open AccessArticle

Crop Yield Prediction Using Multitemporal UAV Data and Spatio-Temporal Deep Learning Models

by Petteri Nevavuori, Nathaniel Narra, Petri Linna and Tarmo Lipping

Remote Sens. 2020, 12(23), 4000; https://0-doi-org.brum.beds.ac.uk/10.3390/rs12234000 - 07 Dec 2020

Cited by 64 | Viewed by 8732

Abstract

Unmanned aerial vehicle (UAV) based remote sensing is gaining momentum worldwide in a variety of agricultural and environmental monitoring and modelling applications. At the same time, the increasing availability of yield monitoring devices in harvesters enables input-target mapping of in-season RGB and crop yield data in a resolution otherwise unattainable by openly availabe satellite sensor systems. Using time series UAV RGB and weather data collected from nine crop fields in Pori, Finland, we evaluated the feasibility of spatio-temporal deep learning architectures in crop yield time series modelling and prediction with RGB time series data. Using Convolutional Neural Networks (CNN) and Long-Short Term Memory (LSTM) networks as spatial and temporal base architectures, we developed and trained CNN-LSTM, convolutional LSTM and 3D-CNN architectures with full 15 week image frame sequences from the whole growing season of 2018. The best performing architecture, the 3D-CNN, was then evaluated with several shorter frame sequence configurations from the beginning of the season. With 3D-CNN, we were able to achieve 218.9 kg/ha mean absolute error (MAE) and 5.51% mean absolute percentage error (MAPE) performance with full length sequences. The best shorter length sequence performance with the same model was 292.8 kg/ha MAE and 7.17% MAPE with four weekly frames from the beginning of the season. Full article

(This article belongs to the Special Issue Deep Learning Methods for Crop Monitoring and Crop Yield Prediction)

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

Deep Learning Methods for Crop Monitoring and Crop Yield Prediction

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (7 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI