Chlorophyll is an essential pigment for photosynthesis in crops, and leaf chlorophyll content can be used as an indicator for crop growth status and help guide nitrogen fertilizer applications. Estimating crop chlorophyll content plays an important role in precision agriculture. In this study, a variable, rate of change in reflectance between wavelengths ‘a’ and ‘b’ (RCRW_a-b), derived from in situ hyperspectral remote sensing data combined with four advanced machine learning techniques, Gaussian process regression (GPR), random forest regression (RFR), support vector regression (SVR), and gradient boosting regression tree (GBRT), were used to estimate the chlorophyll content (measured by a portable soil–plant analysis development meter) of rice. The performances of the four machine learning models were assessed and compared using root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R²). The results revealed that four features of RCRW_a-b, RCRW_{551.0–565.6}, RCRW_{739.5–743.5}, RCRW_{684.4–687.1} and RCRW_{667.9–672.0}, were effective in estimating the chlorophyll content of rice, and the RFR model generated the highest prediction accuracy (training set: RMSE = 1.54, MAE =1.23 and R² = 0.95; validation set: RMSE = 2.64, MAE = 1.99 and R² = 0.80). The GPR model was found to have the strongest generalization (training set: RMSE = 2.83, MAE = 2.16 and R² = 0.77; validation set: RMSE = 2.97, MAE = 2.30 and R² = 0.76). We conclude that RCRW_a-b is a useful variable to estimate chlorophyll content of rice, and RFR and GPR are powerful machine learning algorithms for estimating the chlorophyll content of rice.

Rice false smut (RFS), caused by Ustilaginoidea virens, is a significant grain disease in rice that can lead to reduced yield and quality. In order to obtain spatiotemporal change information, multitemporal hyperspectral UAV data were used in this study to determine the sensitive wavebands for RFS identification, 665–685 and 705–880 nm. Then, two methods were used for the extraction of rice false smut-infected areas, one based on spectral similarity analysis and one based on spectral and temporal characteristics. The final overall accuracy of the two methods was 74.23 and 85.19%, respectively, showing that the second method had better prediction accuracy. In addition, the classification results of the two methods show that the areas of rice false smut infection had an expanding trend over time, which is consistent with the natural development law of rice false smut, and also shows the scientific nature of the two methods.

The pentatricopeptide repeat (PPR) gene family is one of the largest gene families in land plants. However, current knowledge about the evolution of the PPR gene family remains largely limited. In this study, we performed a comparative genomic analysis of the PPR gene family in O. sativa and its wild progenitor, O. rufipogon, and outlined a comprehensive landscape of gene duplications. Our findings suggest that the majority of PPR genes originated from dispersed duplications. Although segmental duplications have only expanded approximately 11.30% and 13.57% of the PPR gene families in the O. sativa and O. rufipogon genomes, we interestingly obtained evidence that segmental duplication promotes the structural diversity of PPR genes through incomplete gene duplications. In the O. sativa and O. rufipogon genomes, 10 (~33.33%) and 22 pairs of gene duplications (~45.83%) had non-PPR paralogous genes through incomplete gene duplication. Segmental duplications leading to incomplete gene duplications might result in the acquisition of domains, thus promoting functional innovation and structural diversification of PPR genes. This study offers a unique perspective on the evolution of PPR gene structures and underscores the potential role of segmental duplications in PPR gene structural diversity.

Wild upland rice species, including Oryza granulata, possess unique characteristics that distinguish them from other Oryza species. For instance, O. granulata characteristically has a GG genome and is accordingly classified as a basal lineage of the genus Oryza. Here, we deployed a versatile hybrid approach by integrating Illumina and PacBio sequencing data to generate a high-quality mitochondrial genome (mitogenome) assembly for O. granulata. The mitogenome of O. granulata was 509,311 base pairs (bp) with sixty-seven genes comprising two circular chromosomes, five ribosomal RNA (rRNA) coding genes, twenty-five transfer RNA (tRNA) coding genes, and thirty-seven genes coding for proteins. We identified a total of 378 simple sequence repeats (SSRs). The genome also contained 643 pairs of dispersed repeats comprising 340 palindromic and 303 forward. In the O. granulata mitogenome, the length of 57 homologous fragments in the chloroplast genome occupied 5.96% of the mitogenome length. Collinearity analysis of three Oryza mitogenomes revealed high structural variability and frequent rearrangements. Phylogenetic analysis showed that, compared to other related genera, O. granulata had the closest genetic relationship with mitogenomes reported for all members of Oryza, and occupies a position at the base of the Oryza phylogeny. Comparative analysis of complete mitochondrial genome assemblies for Oryza species revealed high levels of mitogenomic diversity, providing a foundation for future conservation and utilization of wild rice biodiversity.