Rice blast (RB), a devastating fungal disease, causes severe yield losses worldwide and demands accurate severity quantification for effective management. Remote sensing has been demonstrated useful in disease monitoring and offers a scalable solution, but the phenology challenges the robustness of the model built for spectroscopic severity quantification. Since the variations induced by phenology are closely confounded with the infection progression, it is crucial to identify the specific plant traits that explain the inconsistency in disease severity (DS) estimation while mitigating the phenological influence. To address this issue, this study proposed a novel approach by extending the PROSPECT+SAIL model to account for the optical effects induced in RB-infected rice plants. By introducing DS into PROSPECT simulations based on spectral mixture analysis and lesion optical measurements, the use of RB-extended PROSPECT decreased the leaf simulation errors by up to 36.3 % in the crucial spectral regions for RB monitoring. Subsequently, such an extension enabled the generation of synthetic datasets for disentangling phenological versus RB-induced physiological effects. The sensitivity and disentanglement analysis revealed that leaf chlorophyll content was the primary factor that compromises the relationship between DS and the rice blast index (RIBInir), which was designed for RB severity quantification. After correcting for these effects by normalizing RIBInir with an optimized chlorophyll-sensitive vegetation index (nRIBInir), estimation accuracies significantly improved with an increment of R2 from 0.67 to 0.79, and rRMSE decreased by 9 %, particularly for vegetative samples with mild infection (R2 increased by 0.51). Consequently, the proposed nRIBInir overcame the underestimation of severe infection areas in both severity quantification and spatial mapping. The adapted nRIBInir for drone and satellite sensors also exhibited great performance in DS estimation. Our findings suggest that RB-extended PROSAIL simulations facilitate mitigating the phenological influence with reliable validations and mechanistic interpretation. Moreover, the adaptation flexibility and robustness of nRIBInir ensured its potential in practical applications including resistance breeding, disease tracking, and precision fungicide management at various scales.

Apocynum pictum Schrenk, a halophyte, is commonly used as a traditional Chinese medicine, tea, and fiber crop. To improve the growth of A. pictum in saline soil, its responses to halotolerant plant growth-promoting bacteria (PGPB) were investigated at germination and during early growth stages. Inoculation with either Enterobacter sp. Av16 or Acinetobacter sp. Av23 significantly improved seed germination percentage and alleviated the adverse effects of salinity on seedling growth of A. pictum. Under salt stress, PGPB increased leaf area and improved photosynthetic pigments, including chlorophyll a+b and carotenoids, as well as intercellular carbon dioxide (Ci) and transpiration rate (Tr). More importantly, PGPB alleviated salt-induced damage to the photosynthetic apparatus by stabilizing the photosystems and optimizing electron transport processes. This was evidenced by increases in the density of reaction centers per cross-section (RC/CSm) and the efficiencies of electron transfer to photosystem I (δRo and ΦRo). Consequently, PGPB improved chlorophyll fluorescence and key photosynthetic parameters, including the maximum quantum yield (ΦPo), performance index on absorption basis (PIabs), overall performance index (PItotal), and net photosynthetic rate (Pn). Furthermore, PGPB activated antioxidant enzymes, such as superoxide dismutase (SOD) and catalase (CAT), reducing the accumulation of reactive oxygen species (ROS) in A. pictum. In summary, PGPB enhanced A. pictum seed germination and photosynthetic capacity by stabilizing photosystems, improving stomatal gas exchange, and mitigating oxidative stress under salt stress. These findings highlight the potential of PGPB inoculation as a sustainable strategy to enhance salt resilience in A. pictum.

Accurate monitoring of key growth stages in rice is crucial for precision fertilization and irrigation scheduling, as well as timely harvesting. Remote sensing products often suffer from reduced accuracy when estimating crop phenology. Process-based models perform well at field scale, yet their large-scale deployment is hindered by scarce parameter data and limited real-time forcing. This study integrates remote sensing-estimated growth stage data into a crop model, using the first layer of the two-layer parameter optimization to generate estimates for the entire growth period. Subsequently, the growth stage results estimated based on multiple remote sensing vegetation indices are combined with those generated by the first-layer optimization strategy, and the second layer of the two-layer parameter optimization strategy is applied to further improve the prediction accuracy. The results show that the average RMSE for estimating rice growth stages using remote sensing vegetation indices is 9.2 days. The single-layer parameter optimization strategy fills in the key growth stages that remote sensing methods cannot accurately estimate, resulting in an average RMSE of 9.3 days. The two-layer parameter optimization strategy proposed in this study reduces the average RMSE to 5.3 days, significantly improving the accuracy of full-growth period estimation for rice. Cross-year and multi-variety tests confirmed the method's high robustness, showing an average RMSE reduction of 4.8 days over the single-layer method and demonstrating outstanding performance in early growth stage estimation. Regional-scale results show that the proposed method accurately captures spatial variations caused by climate and management differences, with minimal simulation errors. It demonstrates good performance in improving the accuracy and stability of rice growth stage estimation, providing a novel technical approach for crop growth stage monitoring.

Accurately predicting the phenological stages of different wheat genotypes under varying environmental conditions is critical for crop management optimization and breeding varieties with broad environmental adaptability. Process-based crop growth models can simulate the comprehensive interactive effects between genotypes, environmental conditions, and management practices, making them useful tools for quantitatively predicting and evaluating crop phenotype. However, existing models frequently fail to account for the impact of extreme weather conditions on crop growth stages, resulting in low predictive accuracy. This study considers the wheat heading date as an example and proposes a method that integrates a Long Short-Term Memory (LSTM) with two widely used wheat crop growth models (APSIM-Wheat and WheatGrow), to improve the prediction accuracy of the heading date for wheat breeding populations. The data-model integration considers the effects of three extreme climate indices on wheat phenology, which are typically ignored in wheat growth models. Using three wheat breeding populations with 1142 genotypes across multiple ecological sites in China and Europe, we validate the effectiveness and robustness of the integrated models (APSIM-Wheat-LSTM, WheatGrow-LSTM). Results based on leave-one-environment-out (LOEO) cross-validation strategy show that the integrated models achieved higher accuracy and stability in predicting the heading date compared to purely data-driven machine learning methods and standalone crop growth models. The integrated method also demonstrates good transferability and generalisation ability across different crop growth models and populations. The importance analysis using the explanatory machine learning method (GradientSHAP) show that the integrated models had different feature effects for predicting heading dates in different populations, reflecting the prediction mechanism of the models in complex environments. Overall, the data-model integration method, using the advantage of both the strong mechanization of crop growth models and the high predictability of LSTM, could further improve the accuracy of predicting wheat heading date. The study results provide critical technical support for the quantitative prediction of crop phenology in intelligent crop breeding.

Rice blast (RB) is a global fungal threat that occurs over multiple growth stages. The spatially explicit mapping of RB severity with remote sensing is crucial for precision crop protection. However, the interactions between spectral variations caused by the pathogen infection and phenological growth remain poorly understood in disease monitoring. This interference prevents the successful mapping of disease dynamics by introducing substantial errors in areas dominated by healthy plants. This study aimed to reveal the phenological influence on RB detection and to determine key spectral indicators for accurate classification for eliminating the interference of healthy plants on severity assessments. To achieve this goal, experimental data across growth stages were collected and comprised ground truth evaluations to derive the disease index (DI), and ground-based canopy reflectance and hyperspectral images acquired by an unpiloted aerial system (UAS). These datasets were used to examine the spectral responses to both i) RB infection, and ii) phenology, assessing the false positives obtained in the RB detection. Moreover, a two-step method was applied including the RB detection based on a novel feature selection method termed sequential importance selection (SIS) and the DI estimation using linear models based on rice blast indices (RIBIs). The results demonstrated that the spectral signatures in responses to phenology and RB infection were highly similar in the red and near-infrared regions, as well as in traditional vegetation indices (VIs) associated with plant traits. Such similarity yielded considerable false positive rates (FPR) in RB detection and pseudo-DI in healthy plots when applying individual VIs. In RB detection, the VIs selected by SIS (VISIS) achieved significantly higher overall accuracy (OA) and lower FPR than the best RIBI variant across multiple phenological phases (VISIS: OA = 92 %, F1 = 0.93, FPR = 0.13; aRIBInir: OA = 70.7 %, F1 = 0.75, FPR = 0.36). Moreover, the proposed two-step approach eliminated false positives and wrong DI estimation effectively in healthy plants. Our findings suggested the potential of feature selection in overcoming the phenological influence in RB detection, as well as the necessity of disease detection before severity quantification in eliminating the pseudo severity estimates in healthy plants.

Image fusion aims to integrate complementary information across modalities to generate high-quality fused images, thereby enhancing the performance of high-level vision tasks. While global spatial modeling mechanisms show promising results, constructing long-range feature dependencies in the spatial domain incurs substantial computational costs. Additionally, the absence of ground-truth exacerbates the difficulty of capturing complementary features effectively. To tackle these challenges, we propose a Residual Prior-driven Frequency-aware Network, termed as RPFNet. Specifically, RPFNet employs a dual-branch feature extraction framework: the Residual Prior Module (RPM) extracts modality-specific difference information from residual maps, thereby providing complementary priors for fusion; the Frequency Domain Fusion Module (FDFM) achieves efficient global feature modeling and integration through frequency-domain convolution. Additionally, the Cross Promotion Module (CPM) enhances the synergistic perception of local details and global structures through bidirectional feature interaction. During training, we incorporate an auxiliary decoder and saliency structure loss to strengthen the model's sensitivity to modality-specific differences. Furthermore, a combination of adaptive weight-based frequency contrastive loss and SSIM loss effectively constrains the solution space, facilitating the joint capture of local details and global features while ensuring the retention of complementary information. Extensive experiments validate the fusion performance of RPFNet, which effectively integrates discriminative features, enhances texture details and salient objects, and can effectively facilitate the deployment of the high-level vision task.

The expanding utilization of unmanned aerial vehicle (UAV) remote sensing (RS) technology has significantly advanced crop monitoring and detection. Despite its widespread application, the use of UAVs for examining rice grain starch accumulation (GSA) remains in its infancy. The preflowering nutritional organs' nonstructural carbohydrate transport and the postflowering plant's photosynthesis products are the primary sources of GSA. This study constructs a dynamic change curve based on the spectral index (SI) red edge re-normalized different vegetation index (RERDVI) before rice flowering. It introduces a novel indicator, the preflowering biomass accumulation dynamics (PBAD), identified through the dynamic curve's distinct shape characteristics. Results show that PBAD has a good correlation with the aboveground biomass (AGB) at different preflowering stages. After flowering, a nutrient distribution composite index (NDCI) is developed by combining SIs and color indices (CIs), providing a precise monitoring tool for the nitrogen harvest index (NHI), which is important in GSA. By comprehensively considering preflowering nonstructural carbohydrate accumulation (AGB), postflowering photosynthetic capacity (NHI), canopy temperature depression (CTD) sensitive to GSA, and meteorological factors (sunshine duration (SSD) and precipitation), a GSA estimation model based on multisource RS data fusion was constructed using a multiple linear regression (MLR), random forest regression (RFR), and extreme gradient boosting (XGBoost). This approach significantly improved the accuracy of GSA estimation, with the XGBoost model achieving a validation R(2 )of 0.76 and a root mean square error (RMSE) of 0.11 kg/m2 on a multiecological dataset, notably reducing the underestimation observed in traditional linear models.

Rapid and accurate nitrogen (N) diagnosis plays a crucial role in precise N fertilizer management of wheat. However, most existing N diagnosis models based on proximal fluorescence sensors' indicators are confined to a single growth stage, thereby limiting the accuracy and universality of models. Therefore, this study aimed to construct and evaluate wheat N diagnosis models based on proximal fluorescence sensors across growth stages by fusing multi -source data. Six field experiments conducted over four years, involved diverse planting densities, wheat varieties, and N rates. These experiments were performed to investigate the relationship between optical indicators obtained from Dualex 4 and Multiplex 3, and both the plant N accumulation (PNA) and the N nutrition index (NNI). The dualex indicators were extended to the canopy level (canopy_dualex indicators) by the leaf area index (LAI). In addition to formulating N nutrition diagnostic models based on the three optical indicators solely, we further integrated meteorological factors, soil basic fertility, and cultivation practices to construct dynamic N diagnosis models coupling with machine learning algorithms. Fusing multi -source data significantly improved the R2, resulting in an increase of 0.20 and 0.29 when predicting PNA for dualex and multiplex, respectively. The canopy_dualex indicator consistently performed best in predicting both PNA (R2 = 0.75, RRMSE = 28.71 %) and NNI (R2 = 0.60, RRMSE = 24.62 %) among the three optical indicators. Moreover, the inclusion of LAI effectively addressed the overfitting issue observed in dualex when fusing multi -source data to construct the models. Consistency tests and ROC curve analyses provided robust evidence that canopy_dualex exhibited the highest consistency and the most powerful diagnostic ability. Additionally, multiplex demonstrated superior performance compared to dualex in predicting PNA and NNI, with higher R2 (0.46-0.50) and lower RRMSE (28.57 %-40.84 %). The results underscored that multi -source data fusion significantly improved the accuracy of universal N nutrition models for wheat across growth stages, leveraging proximal fluorescence sensors to cover the entire wheat growth process. This approach allows for the identification of N nutrition status at any given time, facilitating timely adjustments in N fertilizer management. From the two aspects of feature selection results of multi -source data fusion and the difficulty of obtaining data in the application, it is recommended that the first variable to be added in N nutrition diagnosis of is N application amount. If the target is PNA, the accumulated precipitation (APP) data is collected first. In order to obtain NNI, the soil total N content is considered first. Furthermore, this flexibility offers a convenient and promising option for practical agricultural production.

The rapid and accurate estimation of leaf area index (LAI) through remote sensing holds significant importance for precise crop management. However, the direct construction of a vegetation index model based on multi-spectral data lacks robustness and spatiotemporal expansibility, making its direct application in practical production challenging. This study aimed to establish a simple and effective method for LAI estimation to address the issue of poor accuracy and stability that is encountered by vegetation index models under varying conditions. Based on seven years of field plot trials with different varieties and nitrogen fertilizer treatments, the Kalman filter (KF) fusion method was employed to integrate the estimated outcomes of multiple vegetation index models, and the fusion process was investigated by comparing and analyzing the relationship between fixed and dynamic variances alongside the fusion accuracy of optimal combinations during different growth stages. A novel multi-model integration fusion method, KF-DGDV (Kalman Filtering with Different Growth Periods and Different Vegetation Index Models), which combines the growth characteristics and uncertainty of LAI, was designed for the precise monitoring of LAI across various growth phases of rice. The results indicated that the KF-DGDV technique exhibits a superior accuracy in estimating LAI compared with statistical data fusion and the conventional vegetation index model method. Specifically, during the tillering to booting stage, a high R2 value of 0.76 was achieved, while at the heading to maturity stage, it reached 0.66. In contrast, within the framework of the traditional vegetation index model, the red-edge difference vegetation index (DVIREP) model demonstrated a superior performance, with an R2 value of 0.65, during tillering to booting stage, and 0.50 during the heading to maturity stage, respectively. The multi-model integration method (MME) yielded an R2 value of 0.67 for LAI estimation during the tillering to booting stage, and 0.53 during the heading to maturity stage. Consequently, KF-DGDV presented an effective and stable real-time quantitative estimation method for LAI in rice.

A two-year field experiment was conducted to measure the effects of densification methods on photosynthesis and yield of densely planted wheat. Inter-plant and inter-row distances were used to define ratefixed pattern（RR） and row-fixed pattern（RS） density treatments. Meanwhile, four nitrogen（N） rates（0,144, 192, and 240 kg N ha-1, termed N0, N144, N192, and N240） were applied with three densities（225,292.5, and 360 × 104plants ha-1, termed D225, D292.5, and D360）. The wheat canopy was clipped into three equal vertical layers（top, middle, and bottom layers）, and their chlorophyll density（Ch D） and photosynthetically active radiation interception（FIPAR） were measured. Results showed that the response of Ch D and FIPAR to N rate, density, and pattern varied with different layers. N rate, density, and pattern had significant interaction effects on Ch D. The maximum values of whole-canopy Ch D in the two seasons appeared in N240 combined with D292.5 and D360 under RR, respectively. Across two growing seasons,FIPAR values of RR were higher than those of RS by 29.37% for the top layer and 5.68% for the middle layer, while lower than those of RS by 20.62% for the bottom layer on average. With a low N supply（N0）, grain yield was not significantly affected by density for both patterns. At N240, increasing density significantly increased yield under RR, but D360 of RS significantly decreased yield by 3.72% and 9.00%versus D225 in two seasons, respectively. With an appropriate and sufficient N application, RR increased the yield of densely planted wheat more than RS. Additionally, the maximum yield in two seasons appeared in the combination of D360 with N144 or N192 rather than of D225 with N240 under both patterns, suggesting that dense planting combined with an appropriate N-reduction application is feasible to increase photosynthesis capacity and yield.

Accurate and timely information on winter wheat distribution is essential for agricultural management and food security. However, automated approaches for large-scale winter wheat mapping are often hindered by the scarcity of training data. Moreover, well-trained classification model is usually applicable to specific spatial and temporal scales. This study proposed an automated knowledge transfer approach based on adaptive segmentation of phenological similarity images (KT-SimSeg), to shed the reliance on ground labels and reduce spatiotemporal variability for cross-region/year winter wheat mapping. The optical and radar phenological patterns of winter wheat, constructed by the prior knowledge in source domains, were transferred to target domains and aligned with the temporal sequences of undefined pixels. Two-layer phenological similarity between winter wheat and undefined pixels were calculated as indicators to label undefined pixels automatically based on an adaptive threshold segmentation algorithm. Resulting labeled pixels were further refined and were used to pre- train a random forest (RF) model for winter wheat mapping. The performance of the KT-SimSeg approach was assessed in seven regions across the globe for three years, and further compared with two model transfer approaches based on RF (MT-RF) and one-class support vector machine (MT-OCSVM) classifier. The proposed approach performed well for winter wheat mapping with F1-score values of 0.925 and 0.914 across regions and years, which was superior to either MT-RF (0.733 and 0.913) or MT-OCSVM (0.383 and 0.836). Besides the well- delineated winter wheat parcels, the planting areas detected by the KT-SimSeg also showed strong correlations (R2 R 2 = 0.93 and 0.94) with the reference across spatial and temporal domains. Additionally, the KT-SimSeg could identify winter wheat accurately as early as the heading stage. The proposed approach offers a viable solution to produce high-quality regional winter wheat products without local ground labels, and has potential for knowledge transfer across crop production regions and years in quantitative remote sensing modeling.

Effective plant area index (ePAI) and vertical ePAI profile are important metrics in the description of vegetation canopy structure. Rapid, accurate, and high-throughput acquisition of crop ePAI and vertical ePAI profiles using uncrewed aerial vehicle-borne LiDAR (UAV-borne LiDAR) is significant in screening high-yielding crop varieties. However, the influence of the flight altitude and scan angle of UAV-borne LiDAR on the acquisition efficiency and estimation accuracy of crop structural phenotypes has not yet been quantified. To fill the gap, this study investigated the influence of the flight altitudes (15 m, 30 m and 45 m) and mean scan angles (9(degrees), 12(degrees), 19(degrees), 20(degrees), 25(degrees), 30(degrees), 35(degrees), 38(degrees) and 52(degrees)) of UAV-borne LiDAR on the estimation of wheat canopy ePAI and vertical ePAI profile for various cultivars and nitrogen (N) fertilization rates. The results showed that the ePAI estimation accuracy decreases with the increase of the mean scan angle. Smaller mean scan angles have higher ePAI estimation accuracy and can capture more accurate vertical ePAI profiles. Higher altitudes not only reduce estimation errors due to smaller mean scan angles, but also reduce flight and data processing time, thus reducing overall costs. The interaction of flight altitude and mean scan angle has an extremely significant effect on the estimation accuracy of ePAI (Adj -R-2 = 0.96, p < 0.001). The results also demonstrate that the accuracy could be greatly improved (RMSE reduced by up to 36.6 %) by considering the leaf angle distribution of different wheat canopies in the ePAI estimation based on Beer-Lambert law.

Under salt stress, rice leaves usually accumulate sodium and chloride ions, causing water loss. The consequent nutrition imbalance and damage to photosynthetic systems ultimately affects growth and development. Therefore, early identification of rice salt stress is important for timely amelioration to reduce rice yield loss. Solar induced chlorophyll fluorescence (SIF) shows substantial effectiveness for its quick and sensitive response to early-stage stress, suggesting its potential for early crop stress detection. To further assess the capacity of SIF for salt stress detection, this study conducted field plot experiments with a single rice cultivar across two growth stages jointing and booting. The leaf reflectance spectrum of rice was obtained using an ASD FieldSpec Pro FR portable field spectrometer (Analytical Spectral Devices, Boulder, Colorado, USA) and a leaf clip holder. The leaf solar-induced chlorophyll fluorescence (SIF) spectrum was obtained from an ASD coupling filter and FluoWat, which filters out incident sunlight beyond 650 nm. We calculated nine SIF yield indices (FYs), including TFY687 (upward fluorescence yield at 687 nm), TFY739 (upward fluorescence yield at 739 nm), jFY739 (downward fluorescence yield at 739 nm), totFY687 (total of upward and downward fluorescence yield at 687 nm), totFY739 (total upward and downward fluorescence yield at 739 nm). We also explored the adaptive regulation of three biological rice parameters under salt stress: the net photosynthetic rate (Photo), chlorophyll content (Chl), and maximum photochemical efficiency of photosystem II (Fv/Fm). Photo was the most sensitive to salt stress, and showed significant differences on the first day under salt stress. A salt stress response index (SSRI), which combines physiological and biochemical parameters, was constructed to describe the salt stress level. SSRI showed a significant difference on the first day of salt stress, and the dynamics of SSRI were consistent with that of Photo. In addition, we clarified the change rule of SIF for rice leaves under the salt stress. The gray correlation analysis identified five SIF fluorescence yield indices (FYs) that are highly correlated with SSRI: totFY739, jFY739, TFY739, totFY687, and TFY687. Based on the results of gray correlation analysis, a support vector regression model of SSRI was established, which gave an excellent result as follow: R2 of the calibration for the all dataset, booting dataset, and jointing dataset were 0.74, 0.74, and 0.70, respectively, and R2 of the validation data were 0.71, 0.73, and 0.68. In summary, the proposed method to quantitatively detect rice leaf salt stress based on SIF technology allows the early monitoring of rice leaf salt stress.

Despite global warming, extreme low-temperature stress (LTS) events pose a significant threat to rice production (especially in East Asia) that can significantly impact micronutrient and heavy metal elements in rice. With two billion people worldwide facing micronutrient deficiencies (MNDs) and widespread heavy metal pollution in rice, understanding these impacts is crucial. We conducted detailed extreme LTS experiments with two rice (Oryza sativa L.) cultivars (Huaidao 5 and Nanjing 46) grown under four temperature levels (from 21/27 °C to 6/12 °C) and three LTS durations (three, six, and nine days). We observed significant interaction effects for LTS at different growth stages, durations and temperature levels on the contents and accumulation of mineral elements. The contents of most mineral elements (such Fe, Zn, As, Cu, and Cd) increased significantly under severe LTS at flowering, but decreased under LTS at the grain-filling stage. The accumulations of all mineral elements decreased at the three growth stages under LTS due to decreased grain weight. The contents and accumulation of mineral elements were more sensitive to LTS at the peak flowering stage than at the other two stages. Furthermore, the contents of most mineral elements in Nanjing 46 show larger variation under LTS compared to Huaidao 5. Accumulated cold degree days (ACDD, °C·d) were found to be suitable for quantifying the effects of LTS on the relative contents and accumulations of mineral elements. LTS at the flowering stage will help alleviate MNDs, but may also increase potential health risks from heavy metals. These results provide valuable insights for evaluating future climate change impacts on rice grain quality and potential health risks from heavy metals.

Rapid and accurate estimation of crop yield using remote sensing technology could be an important tool for improved global food security. As an effective probe measuring photosynthesis, sun-induced chlorophyll fluorescence (SIF) has potential for predicting crop yield, particularly when SIF measurements are integrated over an extended time period. However, few studies have investigated how temporal scale, vegetation structure, physiology and environmental factors affect crop yield prediction using SIF. Therefore, in this study we evaluate uncertainties in the relationship between SIF and wheat yield, associated with changes in leaf area index (LAI), chlorophyll a and b content (Cab), photosynthetic active radiation (PAR), and the timing of measurements over a range of temporal scales. Wheat field experiments were carried out over two years. LAI, Cab, PAR and canopy SIF were measured at several temporal scales. We systematically compared the performance of SIF parameters [near-infrared canopy SIF normalized by PAR (SIFyNIR), total near-infrared at photosystem level normalized by PAR (SIFyNIR_tot), and normalized difference fluorescence index (NDFI)] and vegetation indices (VIs) [normalized difference vegetation index (NDVI), and NIR reflectance of vegetation (NIRv)] as predictors of yield estimation. Among the SIF parameters, NDFI appeared to be the most sensitive to LAI and Cab. SIFyNIR_tot at the anthesis stage was the best predictor of wheat yield. SIF outperformed VIs for wheat yield estimation during the late growth period. Moreover, as the temporal scale increased (i.e., as the data values were accumulated over longer intervals of time), the relationship between SIFyNIR and wheat yield tended to be more linear. Overall, the uncertainty in the relationship between SIF and yield was affected more by LAI than Cab, and higher PAR produced a stronger and more stable relationship between SIF and wheat yield. Our findings provide empirical support and an example of an approach for using SIF to predict crop yield, as well as elucidation of the mechanisms underlying the relationship between SIF and production.

Accurate and non-destructive monitoring of wheat nitrogen nutrition is of great significance for field fertilizer management to ensure crop yield and quality, reduce environmental pollution, and improve economic benefits. Compared with spectral vegetation indices (which are sensitive to greenness and structural parameters), or active fluorescence (which is limited to small-scale studies), solar-induced chlorophyll fluorescence (SIF) provides a direct measure of crop response to environmental stress and photosynthetic characteristics. However, there has been few studies comparing agronomic parameters, photosynthetic parameters, vegetation indices and SIF as an indicator of nitrogen status. In this paper, we therefore explore these measures as tools for monitoring nitrogen nutrition. During the 2016–2017 growing season, we conducted a field experiment in Rugao, Jiangsu Province, China, using winter wheat (Triticum aestivum L.) and different nitrogen treatments. The sensitivity of SIF indices, vegetation indices, photosynthetic parameters and agronomic parameters to crop nitrogen status were compared. Our results demonstrated that, compared with vegetation indices and agronomic parameters, the ratio of SIF emission peaks (FY687/FY761) responded to nitrogen status most rapidly at both the leaf and canopy scales, as soon as the fourth day after treatment (DAT4). A wheat nitrogen nutrition index (NNI), based on FY687/FY761, was used to construct a leaf dry matter (LDM-based NNI) diagnostic model, which will be beneficial for monitoring and diagnosing the nitrogen nutrition status of wheat leaves. Our results also illuminate the physiological mechanism that enables SIF to be used as a tool to monitor nitrogen nutrient status, primarily through changes in the proportion of light energy distribution. These findings provide theoretical and technical support for monitoring and diagnosing wheat nitrogen nutrition status based on SIF technology.

Spikelet diseases pose severe threats to crop production and crop protection requires timely evaluation of disease severity (DS). However, most studies have only investigated the spikelet diseases within a short period of crop growth. Few have examined the consistency in DS monitoring accuracy across growth stages. This study aimed to investigate the differences in spectral responses among growth stages and to develop a spectral index (SI), rice spikelet rot index (RSRI), for multi-stage monitoring of the rice spikelet rot disease. Proximal hyperspectral images were collected over spikelets with various levels of DS at heading, anthesis, and grain filling stages. The reflectance was related to the DS extracted from concurrent high-resolution RGB images. The proposed RSRI was evaluated for the DS estimation and lesion mapping across growth stages in comparison with existing SIs. The results demonstrated that the spectral responses to DS in the green and near-infrared regions for filling were weaker than those for anthesis, and blue bands were necessary in DS quantification for early infection. The RSRI-based models exhibited the best validation accuracy for heading and the most consistent performance across growth stages as comparison to other SIs (Heading: R-2 = 0.65; anthesis: R-2 = 0.84; filling: R-2 = 0.78). Moreover, RSRI-based DS maps exhibited the best lesion identification for slightly, mildly, and severely infected spikelets. This study suggests that RSRI could be promising in breeding and crop protection as a novel index for DS estimation regardless of the spikelet ripening effect.

Mapping crop distribution using satellite technology is an effective approach for gaining information about food production over broad, regional scales. However, crop classification in high altitude regions from satellite platforms remains challenging, due to the spatial heterogeneity caused by the complex planting patterns. Moreover, the frequent cloud cover makes it difficult to collect time-series imagery for these regions. Thus, this study used a mosaic of single images of Gaofen-6 data to map the crop distribution in high altitude regions of Xining City and Haidong City prefectures of Qinghai Province, China. To improve the accuracy of the crop classification, random forest-recursive feature elimination (RF-RFE) was used to determine an optimal feature subset from existing spectral, texture and topographic features. Then, a two-layer stacking generalization ensemble model, incorporating Random Forest, XGBoost and AdaBoost, was trained. The results reveal that the stacking algorithm outperformed the other single classifiers, with overall accuracy higher than 85% (87.89% for the optimal feature subset and 85.38% for the original spectral band subset). In addition, the user's and producer's accuracies for wheat, rape and maize field all exceeded 90%. Elevation was the variable with the highest importance score, illustrating its importance in crop classification of high altitude regions. Overall, the framework, combining RF-RFE and a stacking algorithm, can improve the accuracy of the crop classification in high altitude regions.