본 논문에서는 인공 신경망의 일종인 Extreme Learning Machine의 학습 알고리즘을 기반으로 하여 노이즈에 강한 특성을 보이는 퍼지 집합 이론을 이용한 새로운 패턴 분류기를 제안 한다. 기존 인공 신경망에 비해 학습속도가 매우 빠르며, 모델의 일반화 성능이 우수하다고 알려진 Extreme Learning Machine의 학습 알고리즘을 퍼지 패턴 분류기에 적용하여 퍼지 패턴 분류기의 학습 속도와 패턴 분류 일반화 성능을 개선 한다. 제안된 퍼지 패턴 분류기의 학습 속도와 일반화 성능을 평가하기 위하여, 다양한 머신 러닝 데이터 집합을 사용한다.

Extreme Learning Machine 기반 퍼지 패턴 분류기 설계

How much does multi-temporal Sentinel-2 data improve crop type classification?

A timely inventory of agricultural areas and crop types is an essential requirement for ensuring global food security and allowing early crop monitoring practices. Satellite remote sensing has proven to be an increasingly more reliable tool to identify crop types. With the Copernicus program and its Sentinel satellites, a growing source of satellite remote sensing data is publicly available at no charge. Here, we used joint Sentinel-1 radar and Sentinel-2 optical imagery to create a crop map for Belgium. To ensure homogenous radar and optical inputs across the country, Sentinel-1 12-day backscatter mosaics were created after incidence angle normalization, and Sentinel-2 normalized difference vegetation index (NDVI) images were smoothed to yield 10-daily cloud-free mosaics. An optimized random forest classifier predicted the eight crop types with a maximum accuracy of 82% and a kappa coefficient of 0.77. We found that a combination of radar and optical imagery always outperformed a classification based on single-sensor inputs, and that classification performance increased throughout the season until July, when differences between crop types were largest. Furthermore, we showed that the concept of classification confidence derived from the random forest classifier provided insight into the reliability of the predicted class for each pixel, clearly showing that parcel borders have a lower classification confidence. We concluded that the synergistic use of radar and optical data for crop classification led to richer information increasing classification accuracies compared to optical-only classification. Further work should focus on object-level classification and crop monitoring to exploit the rich potential of combined radar and optical observations.

https://www.mdpi.com/2072-4292/10/10/1642/pdf

Synergistic Use of Radar Sentinel-1 and Optical Sentinel-2 Imagery for Crop Mapping: A Case Study for Belgium

Mapping cropland extent of Southeast and Northeast Asia using multi-year time-series Landsat 30-m data using a random forest classifier on the Google Earth Engine Cloud

Abstract Large-scale crop monitoring and yield estimation are important for both scientific research and practical applications. Satellite remote sensing provides an effective means for regional and global cropland monitoring, particularly in data-sparse regions that lack reliable ground observations and reporting. The conventional approach of using visible and near-infrared based vegetation index (VI) observations has prevailed for decades since the onset of the global satellite era. However, other satellite data encompass diverse spectral ranges that may contain complementary information on crop growth and yield, but have been largely understudied and underused. Here we conducted one of the first attempts at synergizing multiple satellite data spanning a diverse spectral range, including visible, near-infrared, thermal and microwave, into one framework to estimate crop yield for the U.S. Corn Belt, one of the world's most important food baskets. Specifically, we included MODIS Enhanced VI (EVI), estimated Gross Primary Production based on GOME-2 solar-induced fluorescence (SIF-GPP), thermal-based ALEXI Evapotranspiration (ET), QuikSCAT Ku-band radar backscatter, and AMSR-E X-band passive microwave Vegetation Optical Depth (VOD) in this study, benchmarked on USDA county-level crop yield statistics. We used Partial Least Square Regression (PLSR), an effective statistical model for dimension reduction, to distinguish commonly shared and unique individual information from the various satellite data and other ancillary climate information for crop yield estimation. In the PLSR model that includes all of the satellite data and climate variables from 2007 to 2009, we assessed the first two major PLSR components and found that the first component (an integrated proxy of crop aboveground biomass) explained 82% variability of modelled crop yield, and the second component (dominated by environmental stresses) explained 15% variability of modelled crop yield. We found that most of the satellite derived metrics (e.g. SIF-GPP, radar backscatter, EVI, VOD, ALEXI-ET) share common information related to aboveground crop biomass (i.e. the first component). For this shared information, the SIF-GPP and backscatter data contain almost the same amount of information as EVI at the county scale. When removing the above shared component from all of the satellite data, we found that EVI and SIF-GPP do not provide much extra information; instead, Ku-band backscatter, thermal-based ALEXI-ET, and X-band VOD provide unique information on environmental stresses that improves overall crop yield predictive skill. In particular, Ku-band backscatter and associated differences between morning and afternoon overpasses contribute unique information on crop growth and environmental stress. Overall, using satellite data from various spectral bands significantly improves regional crop yield predictions. The additional use of ancillary climate data (e.g. precipitation and temperature) further improves model skill, in part because the crop reproductive stage related to harvest index is highly sensitive to environmental stresses but they are not fully captured by the satellite data used in our study. We conclude that using satellite data across various spectral ranges can improve monitoring of large-scale crop growth and yield beyond what can be achieved from individual sensors. These results also inform the synergistic use and development of current and next generation satellite missions, including NASA ECOSTRESS, SMAP, and OCO-2, for agricultural applications.

The shared and unique value of optical, flourescence, thermal and microwave satellite data for estimating large-scale crop yields

Sentinel-1A C-SAR and Sentinel-2A MultiSpectral Instrument (MSI) provide data applicable to the remote identification of crop type. In this study, six crop types (beans, beetroot, grass, maize, potato, and winter wheat) were identified using five C-SAR images and one MSI image acquired during the 2016 growing season. To assess the potential for accurate crop classification with existing supervised learning models, the four different approaches namely kernel-based extreme learning machine (KELM), multilayer feedforward neural networks, random forests, and support vector machine were compared. Algorithm hyperparameters were tuned using Bayesian optimization. Overall, KELM yielded the highest performance, achieving an overall classification accuracy of 96.8%. Evaluation of the sensitivity of classification models and relative importance of data types using data-based sensitivity analysis showed that the set of VV polarization data acquired on 24 July (Sentinel-1A) and band 4 data (Sentinel-2A) had the greate...

/pdf/assessing-the-suitability-of-data-from-sentinel-1a-and-2a-5a30ucto65.pdf

Assessing the suitability of data from Sentinel-1A and 2A for crop classification

The identification and mapping of crops are important for estimating potential harvest as well as for agricultural field management. Optical remote sensing is one of the most attractive options because it offers vegetation indices and some data have been distributed free of charge. Especially, Sentinel-2A, which is equipped with a multispectral sensor (MSI) with blue, green, red, and near-infrared-1 bands at 10 m; red edge 1 to 3, near-infrared-2, and shortwave infrared 1 and 2 at 20 m; and 3 atmospheric bands (band 1, band 9, and band 10) at 60 m, offer some vegetation indices calculated to assess vegetation status. However, sufficient consideration has not been given to the potential of vegetation indices calculated from MSI data. Thus, 82 published indices were calculated and their importance were evaluated for classifying crop types. The two most common classification algorithms, random forests (RF) and support vector machine (SVM), were applied to conduct cropland classification from MSI data. Additionally, super learning was applied for more improvement, achieving overall accuracies of 90.2% to 92.2%. Of the two algorithms applied (RF and SVM), the accuracy of SVM was superior and 89.3% to 92.0% of overall accuracies were confirmed. Furthermore, stacking contributed to higher overall accuracies (90.2% to 92.2%), and significant differences were confirmed with the results of SVM and RF. Our results showed that vegetation indices had the greatest contributions in identifying specific crop types.

/pdf/crop-classification-from-sentinel-2-derived-vegetation-4ebtfgpfdi.pdf

Crop classification from Sentinel-2-derived vegetation indices using ensemble learning

Crop classification maps are useful for estimating amounts of crops harvested, which could help address challenges in food security. Remote-sensing techniques are useful tools for generating crop maps. Optical remote sensing is one of the most attractive options because it offers vegetation indices (VIs) with frequent revisits and has adequate spatial and spectral resolution and some data has been distributed free of charge. However, sufficient consideration has not been given to the potential of VIs calculated from Landsat 8 Operational Land Imager (OLI) data. This article describes the use of Landsat 8 OLI data for the classification of crops in Hokkaido, Japan. In addition to reflectance, VIs calculated from simple formulas that consisted of combinations of two or more reflectance wavebands were evaluated, as well as the six components of the Kauth–Thomas transform. The VIs based on shortwave infrared bands (bands 6 or 7) improved classification accuracy, and using a combination of all derived ...

/pdf/mapping-crop-cover-using-multi-temporal-landsat-8-oli-3by393sh3o.pdf

Mapping crop cover using multi-temporal Landsat 8 OLI imagery

Developing techniques are required to generate agricultural land cover maps to monitor agricultural fields. Landsat 8 Operational Land Imager (OLI) offers reflectance data over the visible to shortwave-infrared range. OLI offers several advantages, such as adequate spatial and spectral resolution, and 16 day repeat coverage, furthermore, spectral indices derived from Landsat 8 OLI possess great potential for evaluating the status of vegetation. Additionally, classification algorithms are essential for generating accurate maps. Recently, multi-Grained Cascade Forest, which is also called deep forest, was proposed, and it was shown to give highly competitive performance for classification. However, the ability of this algorithm to generate crop maps with satellite data had not yet been evaluated. In this study, the reflectance at 7 bands and 57 spectral indices calculated from Landsat 8 OLI data were evaluated for its potential for crop type identification.

/pdf/evaluating-metrics-derived-from-landsat-8-oli-imagery-to-map-26b49gxj9z.pdf

Kan-ichiro Mochizuki

Papers

Assessing the suitability of data from Sentinel-1A and 2A for crop classification

Crop classification from Sentinel-2-derived vegetation indices using ensemble learning

Mapping crop cover using multi-temporal Landsat 8 OLI imagery

Evaluating metrics derived from Landsat 8 OLI imagery to map crop cover