Early Season Mapping of Sugarcane by Applying Machine Learning Algorithms to Sentinel-1A/2 Time Series Data: A Case Study in Zhanjiang City, China

Jiang, Hao; Li, Dan; Jing, Wenlong; Xu, Jianhui; Huang, Jianxi; Yang, Ji; Chen, Shuisen

doi:10.3390/rs11070861

Cited by 51 publications

(36 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…0 85 R 2 = In addition, SAR sensors can be used to classify crop types because they are not affected by clouds and atmospheric conditions [24]. Some scientists have investigated the potential of SAR backscatter data for crop mapping using images obtained by Sentinel-1, RADARSAT-1 and 2, EN-VISAT advanced SAR, and phased-array-type L-band SAR [303]- [308]. In recent years, some studies have carried out early season crop (wheat, cotton, spring maize, sugarcane, and rice) type classification based on the combination of optical satellite and SAR data [302], [307]- [309].…”

Section: Early Season Crop Mappingmentioning

confidence: 99%

High-Throughput Estimation of Crop Traits: A Review of Ground and Aerial Phenotyping Platforms

Jin

Zarco‐Tejada

Schmidhalter

et al. 2021

IEEE Geosci. Remote Sens. Mag.

180

View full text Add to dashboard Cite

This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. 2 0274-6638/20©2020IEEE IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE MONTH 2020 C rop yields need to be improved in a sustainable manner to meet the expected worldwide increase in population over the coming decades as well as the effects of anticipated climate change. Recently, genomics-assisted breeding has become a popular approach to food security; in this regard, the crop breeding community must better link the relationships between the phenotype and the genotype. While high-throughput genotyping is feasible at a low cost, highthroughput crop phenotyping methods and data analytical capacities need to be improved. High-throughput phenotyping offers a powerful way to assess particular phenotypes in large-scale experiments, using high-tech sensors, advanced robotics, and imageprocessing systems to monitor and quantify plants in breeding nurseries and field experiments at multiple scales. In addition, new bioinformatics platforms are able to embrace large-scale, multidimensional phenotypic datasets. Through the combined analysis of phenotyping and genotyping data, environmental responses and gene functions can now be dissected at unprecedented resolution. This will aid in finding solutions to currently limited and incremental improvements in crop yields. BACKGROUND Worldwide demand for food will increase through 2050 and beyond due to the increasing global human population. This represents a huge challenge to crop researchers and agricultural policymakers because current yield gain rates will not be sufficient for the demands of population growth, while climate change will make the difficulty even greater. Today's DNA sequencing, marker-assisted breeding, transgenic technology, genome-wide association study (GWAS) approaches, and quantitative trait loci (QTL) identification have been applied, to a limited extent, to improve crop yields [1]-[4]. While it is now relatively easy to select for monogenic traits, current genome sequence datasets have not been sufficiently mined for more genetically complex (multigenic) performance characteristics, at least in part because of the lack of crop phenotypic information collected from real-world field situations. Furthermore, traditional crop growth analysis often involves destructive sampling that is time-consuming and prone to measurement error. At High-Throughput Estimation of Crop Traits A review of ground and aerial phenotyping platforms

show abstract

Section: Early Season Crop Mappingmentioning

confidence: 99%

High-Throughput Estimation of Crop Traits: A Review of Ground and Aerial Phenotyping Platforms

Jin

Zarco‐Tejada

Schmidhalter

et al. 2021

IEEE Geosci. Remote Sens. Mag.

180

View full text Add to dashboard Cite

show abstract

“…(ii) In order to evaluate the performances of different classifiers on each crop type and find the optimal time series lengths for different crops, the F-measure was used. The F-measure is defined as a harmonic mean of precision (P) and recall (R) (see Equation (14)) [70]. Recall equals PA, and precision is the same as UA.…”

Section: Accuracy Assessmentmentioning

confidence: 99%

“…The phenological evolution of each crop structure produces a unique temporal profile of the SAR backscattering coefficient [13,14]. In this way, multi-temporal SAR imagery is an efficient source of time series observations that can be used to monitor growing dynamics for crop classification [15,16].…”

Section: Introductionmentioning

confidence: 99%

“…In previous studies, a lack of high spatial and temporal resolution SAR data was a major challenge for crop identification in southern China, due small-scale structures of plants and a rich variety of crops in the region [14]. Especially for early crop identification, the sufficient frequency of data acquisition in the growth season is very important.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of Three Deep Learning Models for Early Crop Classification Using Sentinel-1A Imagery Time Series—A Case Study in Zhanjiang, China

et al. 2019

Self Cite

View full text Add to dashboard Cite

Timely and accurate estimation of the area and distribution of crops is vital for food security. Optical remote sensing has been a key technique for acquiring crop area and conditions on regional to global scales, but great challenges arise due to frequent cloudy days in southern China. This makes optical remote sensing images usually unavailable. Synthetic aperture radar (SAR) could bridge this gap since it is less affected by clouds. The recent availability of Sentinel-1A (S1A) SAR imagery with a 12-day revisit period at a high spatial resolution of about 10 m makes it possible to fully utilize phenological information to improve early crop classification. In deep learning methods, one-dimensional convolutional neural networks (1D CNNs), long short-term memory recurrent neural networks (LSTM RNNs), and gated recurrent unit RNNs (GRU RNNs) have been shown to efficiently extract temporal features for classification tasks. However, due to the complexity of training, these three deep learning methods have been less used in early crop classification. In this work, we attempted to combine them with an incremental classification method to avoid the need for training optimal architectures and hyper-parameters for data from each time series. First, we trained 1D CNNs, LSTM RNNs, and GRU RNNs based on the full images’ time series to attain three classifiers with optimal architectures and hyper-parameters. Then, starting at the first time point, we performed an incremental classification process to train each classifier using all of the previous data, and obtained a classification network with all parameter values (including the hyper-parameters) at each time point. Finally, test accuracies of each time point were assessed for each crop type to determine the optimal time series length. A case study was conducted in Suixi and Leizhou counties of Zhanjiang City, China. To verify the effectiveness of this method, we also implemented the classic random forest (RF) approach. The results were as follows: (i) 1D CNNs achieved the highest Kappa coefficient (0.942) of the four classifiers, and the highest value (0.934) in the GRU RNNs time series was attained earlier than with other classifiers; (ii) all three deep learning methods and the RF achieved F measures above 0.900 before the end of growth seasons of banana, eucalyptus, second-season paddy rice, and sugarcane; while, the 1D CNN classifier was the only one that could obtain an F-measure above 0.900 for pineapple before harvest. All results indicated the effectiveness of the solution combining the deep learning models with the incremental classification approach for early crop classification. This method is expected to provide new perspectives for early mapping of croplands in cloudy areas.

show abstract

“…Information about crop planting area and spatial distribution is of significance for understanding regional crop production and food security [1,2]. Remote sensing has been increasingly used for crop acreage surveys, given increasing data availability and improved spatial, temporal, and spectral resolutions [1,3,4], together with advances in machine learning classifiers [5,6] and sampling technologies [7,8]. While increasing data and emerging algorithms have provided unprecedented opportunities for crop mapping, feature selection deserves more attention, as improved feature selection can certainly contribute to improvement in computing efficiency and map accuracy [9][10][11].…”

Section: Introductionmentioning

confidence: 99%

Optimizing Feature Selection of Individual Crop Types for Improved Crop Mapping

et al. 2020

Self Cite

View full text Add to dashboard Cite

Accurate crop planting area information is of significance for understanding regional food security and agricultural development planning. While increasing numbers of medium resolution satellite imagery and improved classification algorithms have been used for crop mapping, limited efforts have been made in feature selection, despite its vital impacts on crop classification. Furthermore, different crop types have their unique spectral and phenology characteristics; however, the different features of individual crop types have not been well understood and considered in previous studies of crop mapping. Here, we examined an optimized strategy to integrate specific features of individual crop types for mapping an improved crop type layer in the Sanjiang Plain, a new food bowl in China, by using all Sentinel-2 time series images in 2018. First, an automatic spectro-temporal feature selection (ASTFS) method was used to obtain optimal features for individual crops (rice, corn, and soybean), including sorting all features by the global separability indices for each crop and removing redundant features by accuracy changes when adding new features. Second, the ASTFS-based optimized feature sets for individual crops were used to produce three crop probability maps with the Random Forest classifier. Third, the probability maps were then composited into the final crop layer by considering the probability of each crop at every pixel. The resultant crop layer showed an improved accuracy (overall accuracy = 93.94%, Kappa coefficient = 0.92) than the other classifications without such a feature optimizing process. Our results indicate the potential of the ASTFS method for improving regional crop mapping.

show abstract

Early Season Mapping of Sugarcane by Applying Machine Learning Algorithms to Sentinel-1A/2 Time Series Data: A Case Study in Zhanjiang City, China

Cited by 51 publications

References 40 publications

High-Throughput Estimation of Crop Traits: A Review of Ground and Aerial Phenotyping Platforms

High-Throughput Estimation of Crop Traits: A Review of Ground and Aerial Phenotyping Platforms

Evaluation of Three Deep Learning Models for Early Crop Classification Using Sentinel-1A Imagery Time Series—A Case Study in Zhanjiang, China

Optimizing Feature Selection of Individual Crop Types for Improved Crop Mapping

Contact Info

Product

Resources

About