Use of MODIS EVI to map crop phenology, identify cropping systems, detect land use change and drought risk in Ethiopia – an application of Google Earth Engine

Kibret, Kefyalew Sahle; Marohn, Carsten; Cadisch, Georg

doi:10.1080/22797254.2020.1786466

Cited by 28 publications

(23 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These covariates have been shown to correlate and predict population-level movements, both at the global scale and within sub-Saharan Africa 2 , 30 . Specifically, climatic variables such as aridity, precipitation and EVI have been shown to correlate with agricultural and crop seasons, where seasonal labour migration occurs 44 , 45 , while temperature can correlate with increased travel due to seasonal holidays, including school holidays 46 and religious holidays such as Christmas. Lastly, night-time lights have been shown as an important proxy for seasonal fluctuations in population density, suggesting human movements into and out of cities 2 .…”

Section: Methodsmentioning

confidence: 99%

Practical geospatial and sociodemographic predictors of human mobility

Ruktanonchai

Lai

Utazi

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Understanding seasonal human mobility at subnational scales has important implications across sciences, from urban planning efforts to disease modelling and control. Assessing how, when, and where populations move over the course of the year, however, requires spatially and temporally resolved datasets spanning large periods of time, which can be rare, contain sensitive information, or may be proprietary. Here, we aim to explore how a set of broadly available covariates can describe typical seasonal subnational mobility in Kenya pre-COVID-19, therefore enabling better modelling of seasonal mobility across low- and middle-income country (LMIC) settings in non-pandemic settings. To do this, we used the Google Aggregated Mobility Research Dataset, containing anonymized mobility flows aggregated over users who have turned on the Location History setting, which is off by default. We combined this with socioeconomic and geospatial covariates from 2018 to 2019 to quantify seasonal changes in domestic and international mobility patterns across years. We undertook a spatiotemporal analysis within a Bayesian framework to identify relevant geospatial and socioeconomic covariates explaining human movement patterns, while accounting for spatial and temporal autocorrelations. Typical pre-pandemic mobility patterns in Kenya mostly consisted of shorter, within-county trips, followed by longer domestic travel between counties and international travel, which is important in establishing how mobility patterns changed post-pandemic. Mobility peaked in August and December, closely corresponding to school holiday seasons, which was found to be an important predictor in our model. We further found that socioeconomic variables including urbanicity, poverty, and female education strongly explained mobility patterns, in addition to geospatial covariates such as accessibility to major population centres and temperature. These findings derived from novel data sources elucidate broad spatiotemporal patterns of how populations move within and beyond Kenya, and can be easily generalized to other LMIC settings before the COVID-19 pandemic. Understanding such pre-pandemic mobility patterns provides a crucial baseline to interpret both how these patterns have changed as a result of the pandemic, as well as whether human mobility patterns have been permanently altered once the pandemic subsides. Our findings outline key correlates of mobility using broadly available covariates, alleviating the data bottlenecks of highly sensitive and proprietary mobile phone datasets, which many researchers do not have access to. These results further provide novel insight on monitoring mobility proxies in the context of disease surveillance and control efforts through LMIC settings.

show abstract

Section: Methodsmentioning

confidence: 99%

Practical geospatial and sociodemographic predictors of human mobility

Ruktanonchai

Lai

Utazi

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Since the Moderate Resolution Imaging Spectrometer (MODIS) was launched, it provided time-series vegetation indices (VIs) with a high temporal (daily) and medium spatial resolution (250-500 m) [7]. Many previous studies have exploited the MODIS data to detect the phenological variation of different crops including maize [7], wheat [10,11] and rice [12][13][14], as well as other crops [15][16][17]. In addition, some studies retrieved plant phenology from fine resolution satellite imagery based on new optical sensors [18].…”

Section: Introductionmentioning

confidence: 99%

Improved Accuracy of Phenological Detection in Rice Breeding by Using Ensemble Models of Machine Learning Based on UAV-RGB Imagery

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Accurate and timely detection of phenology at plot scale in rice breeding trails is crucial for understanding the heterogeneity of varieties and guiding field management. Traditionally, remote sensing studies of phenology detection have heavily relied on the time-series vegetation index (VI) data. However, the methodology based on time-series VI data was often limited by the temporal resolution. In this study, three types of ensemble models including hard voting (majority voting), soft voting (weighted majority voting) and model stacking, were proposed to identify the principal phenological stages of rice based on unmanned aerial vehicle (UAV) RGB imagery. These ensemble models combined RGB-VIs, color space (e.g., RGB and HSV) and textures derived from UAV-RGB imagery, and five machine learning algorithms (random forest; k-nearest neighbors; Gaussian naïve Bayes; support vector machine and logistic regression) as base models to estimate phenological stages in rice breeding. The phenological estimation models were trained on the dataset of late-maturity cultivars and tested independently on the dataset of early-medium-maturity cultivars. The results indicated that all ensemble models outperform individual machine learning models in all datasets. The soft voting strategy provided the best performance for identifying phenology with the overall accuracy of 90% and 93%, and the mean F1-scores of 0.79 and 0.81, respectively, in calibration and validation datasets, which meant that the overall accuracy and mean F1-scores improved by 5% and 7%, respectively, in comparison with those of the best individual model (GNB), tested in this study. Therefore, the ensemble models demonstrated great potential in improving the accuracy of phenology detection in rice breeding.

show abstract

“…A successful application of this software requires a preprocessing of the images and further classifications. Recently, the GEE [28,30] have simplified these steps by providing a single platform for server-side image acquisition, preprocessing, processing and visualization. Besides, the methodology in the GEE platform enables online tests and modifications.…”

Section: Introductionmentioning

confidence: 99%

Leaf Area Index Variations in Ecoregions of Ardabil Province, Iran

Andalibi¹,

Ghorbani²,

Moameri³

et al. 2021

Preprint

View full text Add to dashboard Cite

The leaf area index (LAI) is an important vegetation biophysical index that provides broad information on the dynamic behavior of ecosystems productivity and related climate, topography, and edaphic impacts. The spatio-temporal changes of LAI were assessed throughout Ardabil Province, a host of relevant plant communities within the critical ecoregion of a semi-arid climate. In a comparative study, novel data from Google Earth Engine- GEE was tested against traditional ENVI measures to provide LAI estimations. Besides, it is of important practical significance for institutional networks to quantitatively and accurately estimate LAI at large areas in a short time and using appropriate baseline vegetation indices. Therefore, LAI was characterized for ecoregions of Ardabil Province using remote sensing indices extracted from Landsat 8 Operational Land Imager (OLI), including Enhanced Vegetation Index calculated in GEE (EVIG) and ENVI5.3 software (EVIE), as well as Normalized Difference Vegetation Index estimated in ENVI5.3 software (NDVIE). Besides, a new field measurement method, i.e., the LaiPen LP 100 portable device (LP 100), was used to evaluate the accuracy of the derived indices. Accordingly, the LAI was measured on June and July 2020 in 822 ground points distributed in 16 different ecoregions-sub ecoregions having various Plant Functional Types (PFTs) of the shrub, bush, and tree. The analyses revealed heterogeneous spatial and temporal variability in vegetation indices and LAIs within and between ecoregions. The mean (standard deviation) value of EVIG, EVIE, and NDVIE at Province scale yielded 1.1 (0.41), 2.20 (0.78), and 3.00 (1.01), respectively in June, and 0.67 (0.37), 0.80 (0.63), and 1.88 (1.23), in that respect in July. The highest mean values of EVIG-LAI, EVIE-LAI, and NDVIE-LAI in June are found in Meshginshahr (1.40), Meshginshahr (2.80), and Hir (4.33) ecoregions and in July are found in Andabil ecoregion respectively with values of 1.23, 1.5, and 3.64. The lowest mean values of EVIG-LAI, EVIE-LAI, and NDVIE-LAI in June were observed for Kowsar (0.67), Meshginshahr (1.8), and Neur (2.70), ecoregions and in July were for Bilesavar ecoregion respectively with values of 0.31, 0.31, and 0.81. High correlation and determination coefficients (r&gt;0.83 and R2&gt;0.68) between LP 100 and remote sensing derived LAI were observed in all three PFTs (except for NDVIE-LAI in June with r=0.56 and R2=0.31). On average, all three examined LAI measures tended to underestimation compared to LP 100-LAI (r&gt;0.42). The findings of the present study can be promising for effective monitoring and proper management of vegetation and land use in Ardabil Province and other similar areas.

show abstract

Use of MODIS EVI to map crop phenology, identify cropping systems, detect land use change and drought risk in Ethiopia – an application of Google Earth Engine

Cited by 28 publications

References 18 publications

Practical geospatial and sociodemographic predictors of human mobility

Practical geospatial and sociodemographic predictors of human mobility

Improved Accuracy of Phenological Detection in Rice Breeding by Using Ensemble Models of Machine Learning Based on UAV-RGB Imagery

Leaf Area Index Variations in Ecoregions of Ardabil Province, Iran

Contact Info

Product

Resources

About