Vegetation Index Temperature Research Articles

Characteristics of Spatial and Temporal Vegetation Index Variability and Its Responses to Temperature and Precipitation in Mongolia

Characteristics of Spatial and Temporal Vegetation Index Variability and Its Responses to Temperature and Precipitation in Mongolia

Incorporating Multi-Temporal Remote Sensing and a Pixel-Based Deep Learning Classification Algorithm to Map Multiple-Crop Cultivated Areas

The accurate monitoring of crop areas is essential for food security and agriculture, but accurately extracting multiple-crop distribution over large areas remains challenging. To solve the above issue, in this study, the Pixel-based One-dimensional convolutional neural network (PB-Conv1D) and Pixel-based Bi-directional Long Short-Term Memory (PB-BiLSTM) were proposed to identify multiple-crop cultivated areas using time-series NaE (a combination of NDVI and EVI) as input for generating a baseline classification. Two approaches, Snapshot and Stochastic weighted averaging (SWA), were used in the base-model to minimize the loss function and improve model accuracy. Using an ensemble algorithm consisting of five PB-Conv1D and seven PB-BiLSTM models, the temporal vegetation index information in the base-model was comprehensively exploited for multiple-crop classification and produced the Pixel-Based Conv1D and BiLSTM Ensemble model (PB-CB), and this was compared with the PB-Transformer model to validate the effectiveness of the proposed method. The multiple-crop cultivated area was extracted from 2005, 2010, 2015, and 2020 in North China by using the PB-Conv1D combine Snapshot (PB-CDST) and PB-CB models, which are a performance-optimized single model and an integrated model, respectively. The results showed that the mapping results of the multiple-crop cultivated area derived by PB-CDST (OA: 81.36%) and PB-BiLSTM combined with Snapshot (PB-BMST) (OA: 79.40%) showed exceptional accuracy compared to PB-Transformer combined with Snapshot and SWA (PB-TRSTSA) (OA: 77.91%). Meanwhile, the PB-CB (OA: 83.43%) had the most accuracy compared to the pixel-based single algorithm. The MODIS-derived PB-CB method accurately identified multiple-crop areas for wheat, corn, and rice, showing a strong correlation with statistical data, exceeding 0.7 at the municipal level and 0.6 at the county level.

Spatiotemporal monitoring of climate change impacts on water resources using an integrated approach of remote sensing and Google Earth Engine

In this study, a data-driven approach employed by utilizing the product called JRC-Global surface water mapping layers V1.4 on the Google Earth Engine (GEE) to map and monitor the effects of climate change on surface water resources. Key climatic variables affecting water bodies, including air temperature (AT), actual evapotranspiration (ETa), and total precipitation, were analyzed from 2000 to 2021 using the temperature-vegetation index (TVX) and Moderate Resolution Imaging Spectroradiometer (MODIS) products. The findings demonstrate a clear association between global warming and the shrinking of surface water resources in the LUB. According to the results, an increase in AT corresponded to a decrease in water surface area, highlighting the significant influence of AT and ETa on controlling the water surface in the LUB (partial rho of − 0.65 and − 0.68, respectively). Conversely, no significant relationship was found with precipitation and water surface area (partial rho of + 0.25). Notably, the results of the study indicate that over the past four decades, approximately 40% of the water bodies in the LUB remained permanent. This suggests a loss of around 30% of the permanent water resources, which have transitioned into seasonal water bodies, accounting for nearly 13% of the total. This research provides a comprehensive framework for monitoring surface water resource variations and assessing the impact of climate change on water resources. It aids in the development of sustainable water management strategies and plans, supporting the preservation and effective use of water resources.

Integration of microwave satellite soil moisture products in the contextual surface temperature-vegetation index models for spatially continuous evapotranspiration estimation

The contextual surface temperature-vegetation index (TVX) models have been widely used for the retrieval of soil moisture (SM) and evapotranspiration (ET). One of the key premises for their application is to determine quantitatively the theoretical boundaries of this contextual TVX space. Usually these theoretical boundaries are determined based on land surface energy balance principle. Although sound in physical mechanism, the complex parameterization involved has hampered its remote sensing (RS) applications. Our recent studies show that ground-based SM observations can be used for a quick and continuous retrieval of these theoretical boundaries. The main disadvantage lies in its reliance on in-situ SM observations. Fortunately the development of microwave RS technology has made it possible to monitor SM at both regional and global scale. Under this background, a practical framework based on the contextual TVX models was proposed in this paper for continuous ET estimation through the combination of microwave-based SM products and MODIS (Moderate Resolution Imaging Spectroradiometer) products. Daily actual ET over the Southern Great Plains of the United States of America was calculated as the product of net radiation and evaporative fraction (EF). The focus of this framework was to investigate how optical and microwave RS can be combined to achieve a quick and continuous retrieval of EF independently of ground observations. Specifically, EF was retrieved from the contextual TVX models, the theoretical boundaries of which were calibrated at the annual scale based on an optimization scheme. Assuming the seasonal variation of the theoretical dry edge follows a cosine function of solar zenith, the essence of this optimization scheme is to search for the optimal amplitude parameter that maximizes the correlation between microwave-based SM observations and soil moisture index retrieved from the contextual TVX models. Two microwave-based SM products including SMAP (Soil Moisture Active Passive) and SMOS (Soil Moisture and Ocean Salinity) were adopted to demonstrate this optimization scheme. The correlation coefficient, root mean square error and bias of EF estimates calibrated by SMAP were 0.700, 0.146 and 0.047, and those achieved by SMOS were 0.663, 0.174 and 0.168, respectively. The optimization scheme has not only made it possible to conduct a continuous monitoring of ET based entirely on RS observations but also achieved the downscaling of microwave satellite SM products. Thus the combination of optical and microwave RS holds great potential for coupled and continuous estimation of SM and ET over large scale.

Air temperature estimation over winter wheat fields by integrating machine learning and remote sensing techniques

Air temperature (Ta) is significant to numerous Earth's surface and agricultural processes. For agricultural fields (e.g., winter wheat), Ta plays an important role in crop growth monitoring, crop yield estimation, and agricultural risk assessment. In this study, a revised Ta estimation model is proposed by integrating the temperature-vegetation index (TVX) method with multiple regression models. Daily Ta from 2013 to 2021 over winter wheat fields in Henan province (the Top 1 winter wheat-producing province in China) was estimated. The revised models utilized the TVX method over regions and periods featuring extensive vegetation coverage, especially during winter wheat growing seasons, then employed three regression models including multivariate linear regression (MLR) model, random forest (RF) machine learning regression model, and deep belief network (DBN) deep learning regression model. The satellite remote sensing observations, meteorological in-situ Ta measurements, and model assimilations were integrated into the revised models to retrieve Ta. Results obtained through methods proposed in this study were calibrated and validated by in-situ Ta measurements from weather networks. The statistical results reveal that the revised methods can produce Ta estimation over winter wheat-planting areas with higher accuracy compared with traditional regression methods, with R2, MAE, and RMSE ranges from 0.915 to 0.971, 1.204 to 2.097 °C, and 1.623 to 2.911 °C, respectively. Integrating the TVX with RF has the best performance with the highest R2 (0.971), lowest MAE (1.204 °C), and lowest RMSE (1.623 °C) over the winter wheat planting area.

Assessing Moisture Content and Its Mitigating Effect in an Urban Area Using the Land Surface Temperature–Vegetation Index Triangle Method

Nowadays, climate change and heat extremes are becoming highly challenging problems in many cities across the globe. One of the solutions to overcome this problem is the use of vegetation, and, in particular, extending the range of overgrown areas, which are sometimes referred to as “urban green areas.” In this paper, the moisture condition and its mitigating effect on Land Surface Temperature in urban areas were examined in Warsaw, Poland, using satellite data. To do so, the so-called “Triangle Method” was employed. The triangle method is based on a Land Surface Temperature–Normalized Difference Vegetation Index (LST-NDVI) scatterplot to calculate the Temperature Vegetation Dryness Index (TVDI) and its modification–quadratic Temperature Vegetation Dryness Index (qTVDI). This article discusses, in detail, the usefulness of the triangle method for the analyses of built-up areas. The drought satellite indices TVDI and qTVDI compared with those of LST, NDVI, and NDBI (Normalized Difference Building Index). The study shows that the triangle method based on LST-NDVI scatterplot analysis is a promising tool for establishing moisture conditions over urban areas and for studying the effect of vegetation impact on urban heat islands. Detailed analysis shows that over an urban area, qTVDI shows better agreement with LST than classic TVDI.

Cumulative temporal vegetation indices from unoccupied aerial systems allow maize (Zea mays L.) hybrid yield to be estimated across environments with fewer flights.

Unoccupied aerial systems (UAS) based high throughput phenotyping studies require further investigation to combine different environments and planting times into one model. Here 100 elite breeding hybrids of maize (Zea mays L.) were evaluated in two environment trials-one with optimal planting and irrigation (IHOT), and one dryland with delayed planting (DHOT). RGB (Red-Green-Blue) based canopy height measurement (CHM) and vegetation indices (VIs) were estimated from a UAS platform. Time series and cumulative VIs, by both summation (ΣVI-SUMs) and area under the curve (ΣVI-AUCs), were fit via machine learning regression modeling (random forest, linear, ridge, lasso, elastic net regressions) to estimate grain yield. VIs were more valuable predictors of yield to combine different environments than CHM. Time series VIs and CHM produced high accuracies (~68-72%), but inconsistent models. A little sacrifice in accuracy (~60-65%) produced consistent models using ΣVI-SUMs and CHM during pre-reproductive vegetative growth. Absence of VIs produced poorer accuracies (by about ~5-10%). Normalized difference type VIs produced maximum accuracies, and flowering times were the best times for UAS data acquisition. This study suggests that the best yielding varieties can be accurately predicted in new environments at or before flowering when combining multiple temporal flights and predictors.

Dynamic traceability effects of soil moisture on the precipitation–vegetation association in drylands

Vegetation growth is critical in characterizing ecosystem carbon sequestration. Water availability profoundly affects the interaction between climate change and vegetation dynamics in drylands. However, the associations of the precipitation–vegetation index (PRE-VI) and temperature–vegetation index (TEM-VI) as well as whether and how the soil moisture modulates PRE-VI and TEM-VI are still unclear. Precipitation contributed substantially much more to vegetation dynamics than temperature, and PRE-VI associations were greater in the Southern Hemisphere than those in the Northern Hemisphere in global drylands. The traceability effects of soil moisture on PRE-VI and TEM-VI were investigated, and a convex shape was observed for PRE-VI as soil moisture increased, but not significant trend for TEM-VI. It showed that moderate soil moisture enhanced PRE-VI associations through the maintenance of reasonable surface–atmosphere feedback to counteract the balance of plant growth and energy collocation. In the past three decades, PRE-VI associations decreased with the increase in soil moisture, suggesting the consistency of the spatial and temporal pattern of the effect of soil moisture on PRE-VI associations in water-limited ecosystems. Our results implied that changes in soil moisture reflect changes in climate–vegetation associations and can guide nature-based solutions to improve ecosystem carbon sink.

Classification of remote sensing time series and similarity metrics for crop type verification

One of the greatest challenges in many machine learning applications is to build robust classification models that reduce calibration efforts, ensure model transferability to unseen data distributions, and handle high semantic resolution datasets with a relatively large number of target classes. We present an operational domain adaptation framework for crop type verification from remote sensing data for integrated administration and control and farm management systems. It is part of the ag|knowledge crop monitoring platform and demonstrates a more robust spatiotemporal model transferability than conventional supervised crop type classification approaches, which use multitemporal and multispectral features to classify the specific characteristics of crop phenology patterns. The proposed method is based on a machine learning model that has been trained on particular similarity metrics between all target crop types. The metrics are derived by quantifying the similarity of vegetation index time series between the observed parcel and the aggregated time series of reference objects for each parcel and crop type. This method achieves higher classification results than a model trained on the pure remote sensing time series data, as the algorithm does not learn the temporal vegetation index patterns, but instead, the adversarial characteristics and the differences between each crop type. Moreover, it also reduces dimensionality as the time series are summarized through the respective similarity metrics. We compare both approaches through different classification algorithms. Overall, the achieved classification accuracy for more than 67 crop types scores more than 80%.

柴达木盆地蒸散发遥感估算与耗水有效性评价

PDF HTML阅读 XML下载 导出引用 引用提醒 柴达木盆地蒸散发遥感估算与耗水有效性评价 DOI: 10.5846/stxb202105211328 作者: 作者单位: 作者简介: 通讯作者: 中图分类号: 基金项目: 青海省重大科技专项(2019-SF-A4);青海省基础研究计划项目(2020-ZJ-715);国家自然科学基金(42071032) Remote sensing estimation of evapotranspiration and efficiency evaluation of water consumption in Qaidam Basin Author: Affiliation: Fund Project: 摘要 | 图/表 | 访问统计 | 参考文献 | 相似文献 | 引证文献 | 资源附件 | 文章评论 摘要:陆面蒸散发(ET)是自然生态系统水分耗散的主要方式,准确把握其时空变化特征,对于区域水资源合理利用与生态环境保护具有重要意义。针对我国西北干旱内陆区实测资料匮乏的现状,基于MODIS产品,构建了具有时空二维属性的地表温度-植被指数特征空间,实现了柴达木盆地陆面蒸散发的时空连续估算;在此基础上,进一步分离土壤蒸发与植被蒸腾,开展研究区自然生态系统耗水有效性评价。结果表明:(1)柴达木盆地近九年多年平均ET为188.75 mm,受降水空间分布格局影响,ET具有明显的从东南向西北减少趋势;(2)土壤蒸发与植被蒸腾多年平均值为171.06 mm和14.26 mm,后者年内峰值出现时间总体比前者晚1个月,具有滞后效应;(3)盆地陆地生态系统多年平均耗水总量为430.94亿m3,其中高效、中效和低效耗水的占比分别为6.55%、52.57%和40.88%。在区域尺度以时空连续的方式揭示了ET水分消耗的有效性,可为基于ET水资源管理目标的实现提供重要科学支撑。 Abstract:Terrestrial evapotranspiration (ET), composed of soil evaporation and plant transpiration, is the main mode of water dissipation in the natural ecosystems. In general, ET returns about two thirds of the annually terrestrial precipitation to the atmosphere on the global scale, and the ratio can reach as high as 80% in arid areas. As a result, accurate knowledge of ET is crucial to understand the water budget as well as its effect on ecosystems. This is particularly important for water resources management and eco-environmental protection in arid regions. Compared with ground-based ET measurements recorded by sparse flux towers, satellite remote sensing (RS) is a suitable tool to map regional ET patterns in a temporally and spatially consistent manner, yielding a series of RS-based ET models with varying mechanisms and degrees of complexity. Considering the sparse distribution of meteorological observations in the Northwest of China, we adopted the surface temperature-vegetation index (TVX) method in this study to estimate daily ET in Qaidam Basin from 2011 to 2019. Uniquely, the theoretical boundaries of the TVX feature space were determined pixel by pixel based on the surface energy balance principle, so ET could be mapped for regions with complex topography in a spatially consistent manner. Then a simple dual-source ET framework was used to partition evapotranspiration into soil evaporation (E) and plant transpiration (T), and finally the water consumption efficiency of natural ecosystems was evaluated by further partitioning E into soil evaporation over bare land and soil evaporation beneath the canopy. All the above schemes were demonstrated with Terra Moderate Resolution Imaging Spectroradiometer (MODIS) products. Results show that the annual ET of Qaidam Basin from 2011 to 2019 decreased at first and then increased, with an average value of 188.75 mm. As for seasonal variations, ET from April to September accounted for 80% of the annual ET with the peak value arising in June or July. Influenced by the spatial patterns of precipitation, the ET presents an obviously decreasing trend from southeast to northwest and from the surrounding mountains to the interior of the basin. Local high ET values in the interior of the basin are mainly distributed around the rivers, lakes, and springs. The annual average E and T in the recent nine years is 171.06 mm and 14.26 mm, respectively. Although the seasonal variations of both E and T follow a trend similar to sinusoidal curves with the peak values observed in summer, the peak of the latter appears one month later than that of the former. In terms of spatial distribution, soil evaporation shares patterns consistent with total ET, but plant transpiration is mainly observed in the southeast of the basin, showing a semi-ring structure. The annually total water consumption of terrestrial ecosystems in the basin is 43.094 billion m3 on average. The corresponding proportion of high-efficiency, medium-efficiency and low-efficiency water consumption is 6.55%, 52.57% and 40.88%, respectively. Due to the extremely low fractional vegetation cover of Qaidam Basin, the amount of water consumption with high-efficiency is much lower than the other two. However, when considered water consumed by bare land and dense canopy, the water consumed by dense canopy per unit area is 297.83 mm, which is much higher than that consumed by bare land. In conclusion, this study reveals the water consumption efficiency of ET in the whole Qaidam Basin in a temporally and spatially consistent manner, which provides important scientific support for ET-based water resources management. 参考文献 相似文献 引证文献

Assessing the Long-Term Evolution of Abandoned Salinized Farmland via Temporal Remote Sensing Data

Salinization in arid or semiarid regions with water logging limits cropland yield, threatening food security. The highest level of farmland salinization, that is, abandoned salinized farmland, is a tradeoff between inadequate drainage facilities and sustainable farming. The evolution of abandoned salinized farmlands is closely related to the development of cropping systems. However, detecting abandoned salinized farmland using time-series remote sensing data has not been investigated well by previous studies. In this study, a novel approach was proposed to detect the dynamics of abandoned salinized farmland using time-series multispectral and thermal imagery. Thirty-two years of temporal Landsat imagery (from 1988 to 2019) was used to assess the evolution of salinization in Hetao, a two-thousand-year-old irrigation district in northern China. As intermediate variables of the proposed method, the crop-specific planting area was retrieved via its unique temporal vegetation index (VI) pattern, in which the shape-model-fitting technology and the K-means cluster algorithm were used. The desert area was stripped from the clustered non-vegetative area using its distinct features in the thermal band. Subsequently, the abandoned salinized farmland was distinguished from the urban area by the threshold-based saline index (SI). In addition, a regression model between electrical conductance (EC) and SI was established, and the spatial saline degree was evaluated by the SI map in uncropped and unfrozen seasons. The results show that the cropland has constantly been expanding in recent decades (from 4.7 × 105 ha to 7.1 × 105 ha), while the planting area of maize and sunflower has grown and the area of wheat has decreased. Significant desalinization progress was observed in Hetao, where both the area of salt-affected land (salt-free area increased approximately 4 × 105 ha) and the abandoned salinized farmland decreased (reduced from 0.45 × 105 ha to 0.19 × 105 ha). This could be mainly attributed to three reasons: the popularization of water-saving irrigation technology, the construction of artificial drainage facilities, and a shift in cropping patterns. The decrease in irrigation and the increase in drainage have deepened the groundwater table in Hetao, which weakens the salt collection capacity of the abandoned salinized farmland. The results demonstrate the promising possibility of reutilizing abandoned salinized farmland via a leaching campaign where the groundwater table is sufficiently deep to stop salinization.

An operational parameterization scheme of surface temperature-vegetation index contextual model for large-scale temporally continuous evapotranspiration estimation: The case study of contiguous United States

A recent review has suggested relatively simple contextual models would remain attractive in the estimation of evapotranspiration (ET). The surface temperature-vegetation index feature space model is a typical representative since it provides direct monitoring of ET using simply and effective contextual information. However, the temporally continuous estimation and large-scale application issues are not well identified at previous studies. Under this background, the main motivation for this study is to develop an operational new parameterization scheme within the feature space framework for large-scale temporally continuous ET estimation. Specifically, the spatial domain division strategy was first designed to obtain the optimal grid division size for large-scale ET estimation. The model boundaries of these sub-regions were parameterized using spatial domain based temporal domain information at seasonal scale. The applicability of new method was demonstrated over the entire contiguous United States (CONUS) in the year 2008 using Moderate Resolution Imaging Spectroradiometer (MODIS) and Global Land Surface Satellite (GLASS) products. The comparison between present method and traditional method indicates that the new parameterization scheme produced at different reference spatial domains has a slight accuracy improvement over the 14 FLUXNET sites. In addition, the new method holds unique advantages in its simplicity and continuity, especially superior in the temporally continuous estimation of ET over a large extended region. The validation results of 14 FLUXNET sites indicate the correlation coefficient (r), mean absolute error (MAE), root mean square error (RMSE) the mean bias (B) values for continuous estimation of daily ET were 0.62, 28.430 W/m2, 36.133 W/m2 and −0.059, respectively. The comparison results with existing ET product also demonstrated the comparable of ET distribution and estimates. Meanwhile, the boundary parameters obtained at seasonal scale also enhanced the physical meanings of feature space model. Consequently, the new parameterization scheme proposed in this study can be regarded as a suitable tool to provide large-scale temporally continuous estimation of ET.

Monitoring crop growth using a canopy structure dynamic model and time series of synthetic aperture radar (SAR) data

ABSTRACT Normalized Difference Vegetation Index (NDVI) time series data are used by agricultural agencies for many essential operational crop monitoring programmes. But optical sensors often miss key growth stages due to cloud cover interference, impacting the performance of operational activities. Although the synergistic use of optical and Synthetic Aperture Radar (SAR) imagery can provide time series data, any SAR-optical integration necessitates building a relationship between these two data sources. The objective of this study was to use a semi-empirical Canopy Structure Dynamics Model (CSDM), Growing Degree Days (GDD), and SAR parameters calibrated to optical NDVI to derive daily estimates of canola crop condition over an entire growing season. RADARSAT-2 Fine Quad-pol and RapidEye images were collected over three years for a study site in western Canada. Object-based image analysis was applied to study the relationship between the optical and SAR time series data. Significant correlations were documented between a number of SAR parameters and optical NDVI, specifically a ratio of backscatter intensities (HH-HV)/(HH+HV), a ratio of volume to surface scattering extracted from the Freeman Durden decomposition, and Entropy from the Cloude-Pottier decomposition. Correlations (r-values) between these SAR parameters and optical NDVI ranged from 0.63 to 0.84 for the three years of data. Based on this analysis, a simple statistical model was used to relate SAR parameters to optical NDVI, creating a SAR-calibrated NDVI (SARcal-NDVI). A CSDM was fit to the SARcal-NDVI for each canola field, constructing a temporal vegetation index curve which captured canopy development from emergence to senescence. Coefficients of determination (R2) were 0.87 0.86 and 0.82 for entropy, the volume-surface scattering ratio, and the ratio of backscatter intensities (HH-HV)/(HH+HV), respectively, demonstrating a good model fit. The CSDM describes well the temporal evolution of SARcal-NDVI. Using the CSDM, SARcal-NDVI and GDD, the canola condition can be estimated for any given day in the growing season. In fact when the CSDM was used to estimate SARcal-NDVI for the exact days of RapidEye acquisitions, correlations with optically derived NDVI were high. The strongest correlations with RapidEye NDVI were reported for the volume-surface scattering ratio (R2 of 0.69 and RMSE of 0.15). The SARcal-NDVI estimated from the CSDM was also physically meaningful. Field-based biomass was significantly correlated (R2 of 0.79) with the SARcal-NDVI calculated using the volume-surface scattering ratio. Although further research is needed to extend this method to other crops, these results demonstrate that SAR data can be used to estimate vegetation conditions and when coupled with a CSDM, integrated into current monitoring operations based on optical NDVI. As a next step, the research team will be assessing SARcal-NDVI in a national operational programme which reports on crop yields using modelling with optical-based NDVI.

Estimation of actual evapotranspiration and its components in an irrigated area by integrating the Shuttleworth-Wallace and surface temperature-vegetation index schemes using the particle swarm optimization algorithm

Daily actual evapotranspiration (ET) and its components – soil evaporation (E) and vegetation transpiration (T) – play a key role in water resource management of irrigated areas. Nevertheless, due to large uncertainties in the parameterization of the resistances in irrigated areas, traditional ET models do not always provide accurate ET estimates, especially for its components. This uncertainty is mainly due to the difficulty of determining the empirical parameters accurately of soil and canopy resistances which is debated for a long time and the error in input variables. This paper proposed an optimized Shuttleworth-Wallace model (SW) using the particle swarm optimization (PSO) algorithm to integrate the original SW with the surface temperature-vegetation index (Ts-VI) triangle models (named Shuttleworth & Wallace_Temperature Vegetation Index model, SW_TVI).The performance of the SW_TVI model was significantly improved by optimizing the soil and canopy resistances in the original SW model using discontinuous regional ET estimates from the Ts-VI model under clear-sky conditions. Compared with the original SW model, the root mean squared error (RMSE) and mean absolute deviation (MAD) of the SW_TVI model were reduced by more than 30%, against in situ measurements in the Heihe River Basin. The Bias of the T/ET ratio was also significantly reduced from -22.3% for the original SW model to -5.5% for the SW_TVI model. The annual contributions of E and T to ET were about 20% and 80%, respectively, and had a strong seasonal variation in the typical irrigated area of China. In summary, the SW_TVI model shows three outstanding advantages: (1) it estimates daily continuous E, T, and total ET with high accuracy; (2) it is very robust and insensitive or slightly sensitive to most input variables and empirical parameters; (3) it is independent from ground data. This new SW_TVI model will benefit water resources management in irrigated areas, particularly in arid and semi-arid regions.

Temporal Vegetation Indices and Plant Height from Remotely Sensed Imagery Can Predict Grain Yield and Flowering Time Breeding Value in Maize via Machine Learning Regression

Unoccupied aerial system (UAS; i.e., drone equipped with sensors) field-based high-throughput phenotyping (HTP) platforms are used to collect high quality images of plant nurseries to screen genetic materials (e.g., hybrids and inbreds) throughout plant growth at relatively low cost. In this study, a set of 100 advanced breeding maize (Zea mays L.) hybrids were planted at optimal (OHOT trial) and delayed planting dates (DHOT trial). Twelve UAS surveys were conducted over the trials throughout the growing season. Fifteen vegetative indices (VIs) and the 99th percentile canopy height measurement (CHMs) were extracted from processed UAS imagery (orthomosaics and point clouds) which were used to predict plot-level grain yield, days to anthesis (DTA), and silking (DTS). A novel statistical approach utilizing a nested design was fit to predict temporal best linear unbiased predictors (TBLUP) for the combined temporal UAS data. Our results demonstrated machine learning-based regressions (ridge, lasso, and elastic net) had from 4- to 9-fold increases in the prediction accuracies and from 13- to 73-fold reductions in root mean squared error (RMSE) compared to classical linear regression in prediction of grain yield or flowering time. Ridge regression performed best in predicting grain yield (prediction accuracy = ~0.6), while lasso and elastic net regressions performed best in predicting DTA and DTS (prediction accuracy = ~0.8) consistently in both trials. We demonstrated that predictor variable importance descended towards the terminal stages of growth, signifying the importance of phenotype collection beyond classical terminal growth stages. This study is among the first to demonstrate an ability to predict yield in elite hybrid maize breeding trials using temporal UAS image-based phenotypes and supports the potential benefit of phenomic selection approaches in estimating breeding values before harvest.

Analysis of Climate Variability and Relation to Vegetation in Garamba National Park from 1990-2020

Climatic factors impact vegetation. Our study was to examine and analyze the climate variability and relationship to vegetation in Garamba National Park of the Democratic Republic of the Congo over the past 30 years (1990 to 2020), then to relate the climatic variables. Mann Kendall’s non parametric test, ANOVA, and p-value tests are used to analyze existing trends and relationships between vegetation cover, climatic factors, land surface temperature (LST) and normalized difference in temperature Vegetation index (NDVI), Enhanced vegetation index (EVI) in Garamba national park which is of particular importance for the network of protected areas of the Democratic republic of Congo because its position at the northern limit of the savanna-forest mosaics gives it a unique biodiversity. The southern part of the park is dominated by grassy shrub savannas. The results showed that: 1) In Garamba, the monthly correlation coefficient of Kendall and Pearsan between temperature and precipitation are negative respectively 0.763 and −0.876 (p-value < 0.00001). 2) Annually during the three decades in Garamba, the correlation between precipitation and NDVI is significant 0.416 (Kendall) and 0.496 (Pearsan); the same between precipitation and EVI 0.291 (Kendall) and 0.496 (Pearsan) while LST and precipitation are negatively correlated (p-value < 0.00001).

Coupled and continuous estimation of soil moisture and evaporative fraction within the remotely sensed surface temperature-vegetation index framework

Numerous studies have focused on the retrieval of soil moisture (SM) and evaporative fraction (EF) based on the surface temperature-vegetation index (TVX) framework. However, few literatures have investigated whether these two variables can be retrieved simultaneously under the same TVX framework. Besides, most previous studies only demonstrated the application of the TVX framework under clear sky conditions. The estimation of SM and EF under partially cloudy conditions is still a challenging task. The main motivation for this study is to develop an observation-driven optimization framework combined with TVX method for coupled and continuous estimation of SM and EF. Specifically, the optimization scheme was designed to construct the constraints and objective functions of the TVX framework at seasonal scale. In-situ SM and EF measurements were utilized to calibrate the theoretical boundaries of the TVX framework, respectively. The applicability of this new scheme was demonstrated over the Southern Great Plains (SGP) of the United States of America in the year 2005 using Moderate Resolution Imaging Spectroradiometer (MODIS) products. The comparisons between present method and previous traditional TVX models indicate that the accuracy of the optimization scheme produced using only one site for calibration has reached a comparable level over the whole study domain. However, the new scheme holds unique advantages in simplicity and continuity. It has not only circumvented the complex parameterization scheme of theoretical TVX framework, but also achieved estimation of SM and EF under partially cloudy conditions. The validation results of SM estimates show that the absolute value of correlation coefficient (r) under clear and partially cloudy sky conditions was 0.51 and 0.43, respectively. The validation results of EF estimates indicate that the r and root mean square error (RMSE) under clear sky conditions was 0.70 and 0.163. In contrast, the r and RMSE under partially cloudy conditions was 0.66 and 0.158. In addition, the coupled estimation of SM and EF means that these two objective variables can be interconverted into each other within the optimization framework. Thus either SM or EF can be used to calibrate the theoretical dry edge that applies to the estimation of both variables.

Evaluation of the Performance of the Integration of Remote Sensing and Noah Hydrologic Model for Soil Moisture Estimation in Hetao Irrigation Region of Inner Mongolia

As an important parameter in Land surface system research, surface soil moisture (SSM) links the surface water and groundwater that plays a key role in water resources, agricultural management and global warming studies. Remote sensing techniques provide a direct and convenient means to estimate SSM on a regional scale. In this study, the performance of the normalized land surface temperature-vegetation index (LST-VI) model was evaluated using the in situ soil moisture measurements at Hetao irrigation region of Inner Mongolia that is a representative semi-arid area with relatively uniform underlying surface. The model was used to estimate soil moisture from HJ-1B and Landsat 8 images on clear days in 2014–2017. The overall SSM estimation accuracy was high, and the average RMSE was approximately 0.04 m3/m3. Moreover, a systematic sensitivity analysis was conducted for the input parameters and other impact factors. The results demonstrated that the model could credibly monitor the regional surface soil water content.

An observation-driven optimization method for continuous estimation of evaporative fraction over large heterogeneous areas

Ground-based evaporative fraction (EF) observations have been used widely for validation purposes in previous remote sensing-based EF models. Few studies have investigated whether such measurements can be utilized for calibration use. In this paper, an observation-driven optimization method is proposed to quantify EF over a large heterogeneous area within the surface temperature-vegetation index framework. It is designed at both daily scale and seasonal scale with MODIS products and in-situ EF observations over the Southern Great Plains in the US. The goal is to search for the optimal dry edge within the allowable range that minimizes the difference between the estimated and observed EF of a given site. Results show that the accuracy produced using only one site for calibration has reached a level comparable to those produced by traditional triangle methods. Compared with the daily-scale optimization method, the seasonal-scale optimization method has not only demonstrated its superiority in accuracy but also held distinctive advantages over the traditional triangle methods. Specifically, the dry edge produced by our optimization method holds true under both clear sky and partially cloudy conditions. This has not only bypassed the repetitive work of previous triangle methods but also made it possible to conduct a continuous monitoring of EF. Besides, the optimization method is characterized by its simplicity in algorithm, stability in accuracy and extensibility in parameterization, which makes it a suitable tool for providing a quick and reasonable estimation of EF over large heterogeneous areas from a limited number of in-situ EF observations.

Developing a Gap-Filling Algorithm Using DNN for the Ts-VI Triangle Model to Obtain Temporally Continuous Daily Actual Evapotranspiration in an Arid Area of China

Temporally continuous daily actual evapotranspiration (ET) data play a critical role in water resource management in arid areas. As a typical remotely sensed land surface temperature (LST)-based ET model, the surface temperature-vegetation index (Ts-VI) triangle model provides direct monitoring of ET, but these estimates are temporally discontinuous due to cloud contamination. In this work, we present a gap-filling algorithm (TSVI_DNN) using a deep neural network (DNN) with the Ts-VI triangle model to obtain temporally continuous daily actual ET at regional scale. The TSVI_DNN model is evaluated against in situ measurements in an arid area of China during 2009–2011 and shows good agreement with eddy covariance (EC) observations. The temporal coverage was improved from 16.1% with the original Ts-VI tringle model to 67.1% with the TSVI_DNN model. The correlation coefficient (R), root mean square error (RMSE), bias, and mean absolute difference (MAD) are 0.9, 0.86 mm d−1, −0.16 mm d−1, and 0.65 mm d−1, respectively. When compared with the National Aeronautics and Space Administration (NASA) official MOD16 version 6 ET product, estimates of ET using TSVI_DNN are improved by approximately 49.2%. The method presented here can potentially contribute to enhanced water resource management in arid areas, especially under climate change.