Artificial Neural Networks and Data Mining Techniques for Summer Crop Discrimination: A New Approach

Abstract

The title and author names are listed on this sheet as they will be published, both on your paper and on the Table of Contents. Please review and ensure the information is correct and advise us if any changes need to be made. In addition, please review your paper as a whole for typographical and essential corrections.Your PDF proof has been enabled so that you can comment on the proof directly using Adobe Acrobat. For further information on marking corrections using Acrobat, please visit http://journalauthors.tandf.co.uk/production/acrobat.asp; https://authorservices.taylorandfrancis.com/how-to-correct-proofs-with-adobe/ The CrossRef database (www.crossref.org/) has been used to validate the references. AUTHOR QUERIES Q1'This procedure decomposed the annual variation of the EVI and are represented by the mean (H0), by the phase that indicates the cycle of the culture in intervals of 0 -360 , and by the Amplitude (H1) that indicates the maximum vegetation variation for the entire period.' The part of this sentence in bold is unclear. Could author please clarify and reword. Q2There is no mention of (Bouckaert et al. 2010, IBGE -Instituto Brasileiro de Geografia e Estat ıstica 2016) in the text. Please insert a citation in the text or delete the reference as appropriate. Q3Please provide the publisher location "Coutinho et al. 2012". Q4Please provide the publisher location for "K€ oppen and Geiger 1928".

Spatial Extraction of Wheat-Corn Rotation Areas in Sushui River Basin Based on NDVI Differences in Key Phenological Stages

“…Therefore the identification of wheat utilizes the key climatic differences between wheat sowing and tillering as an indicator.The specificity of NDVI growth from planting to tillering period of winter wheat has been applied in spatial extraction of winter wheat [2,[15][16]35]. The identification of summer corn mostly uses the combination of spectral features and models [5,[36][37]; also, the phenological features of summer corn growth cycle are utilized [27,38]. In this study, the planting period and the tasseling period were selected as key periods.…”

“…The spatial recognition methods applied in winter wheat and summer corn include the following three categories: first is to select suitable spectral features or vegetation indices combined with machine learning models for classification and extraction. For example, Junior et al utilized data mining techniques and artificial neural networks to classify maize and soybean with similar phenology [5], while Liu et al used random forests to extract the spatial distribution of soybeans and corn [6]. Second, time series curves are constructed and combined with a priori phenological knowledge to recognize the phenological curves of classified objects, while similarity judgment is performed to extract target crops [7][8].…”

Investigation on the use of ensemble learning and big data in crop identification

“… (15 bands) - > OA (90%). [ 39 ] ANN and PCA TERRA/AQUA-Modis and Landsat-OLI OA (89%) [ 40 ] SVM and RF Unmanned Aerial Vehicle (UAV) images SVM achieved the best crop classification based only on spectral information. [ 41 ] Maximum Likelihood and Minimum Distance Spot-5 images [ 42 ] Polarimetric Correlation Coefficients.…”

Investigating the Use of Street-Level Imagery and Deep Learning to Produce In-Situ Crop Type Information

“…However, for monitoring food security at national-to-global scales, spatially explicit crop type maps are urgently needed [6] With recent advances in analytical methods, data infrastructure and the availability of higherresolution imagery, several recent studies have applied machine learning techniques for crop type recognition. Some of the most successful include support vector machines (SVMs) [7][8][9], random forests [9][10][11][12], decision trees [12][13][14], the maximum likelihood classifier (MLC) [11,15,16], artificial neural networks (ANNs) [11,17] and minimum distance (MD) [11]. Another example is the work undertaken by Mou et al in [16], where the authors proposed a deep recurrent neural network (RNN) for hyperspectral image classification.…”