Advancing common bean (Phaseolus vulgaris L.) disease detection with YOLO driven deep learning to enhance agricultural AI.

Common beans (CB), a vital source for high protein content, plays a crucial role in ensuring both nutrition and economic stability in diverse communities, particularly in Africa and Latin America. However, CB cultivation poses a significant threat to diseases that can drastically reduce yield and quality. Detecting these diseases solely based on visual symptoms is challenging, due to the variability across different pathogens and similar symptoms caused by distinct pathogens, further complicating the detection process. Traditional methods relying solely on farmers' ability to detect diseases is inadequate, and while engaging expert pathologists and advanced laboratories is necessary, it can also be resource intensive. To address this challenge, we present a AI-driven system for rapid and cost-effective CB disease detection, leveraging state-of-the-art deep learning and object detection technologies. We utilized an extensive image dataset collected from disease hotspots in Africa and Colombia, focusing on five major diseases: Angular Leaf Spot (ALS), Common Bacterial Blight (CBB), Common Bean Mosaic Virus (CBMV), Bean Rust, and Anthracnose, covering both leaf and pod samples in real-field settings. However, pod images are only available for Angular Leaf Spot disease. The study employed data augmentation techniques and annotation at both whole and micro levels for comprehensive analysis. To train the model, we utilized three advanced YOLO architectures: YOLOv7, YOLOv8, and YOLO-NAS. Particularly for whole leaf annotations, the YOLO-NAS model achieves the highest mAP value of up to 97.9% and a recall of 98.8%, indicating superior detection accuracy. In contrast, for whole pod disease detection, YOLOv7 and YOLOv8 outperformed YOLO-NAS, with mAP values exceeding 95% and 93% recall. However, micro annotation consistently yields lower performance than whole annotation across all disease classes and plant parts, as examined by all YOLO models, highlighting an unexpected discrepancy in detection accuracy. Furthermore, we successfully deployed YOLO-NAS annotation models into an Android app, validating their effectiveness on unseen data from disease hotspots with high classification accuracy (90%). This accomplishment showcases the integration of deep learning into our production pipeline, a process known as DLOps. This innovative approach significantly reduces diagnosis time, enabling farmers to take prompt management interventions. The potential benefits extend beyond rapid diagnosis serving as an early warning system to enhance common bean productivity and quality.

Assessing methane emissions from paddy fields through environmental and UAV remote sensing variables.

Concerns about methane (CH4) emissions from rice, a staple sustaining over 3.5 billion people globally, are heightened due to its status as the second-largest contributor to greenhouse gases, driving climate change. Accurate quantification of CH4 emissions from rice fields is crucial for understanding gas concentrations. Leveraging technological advancements, we present a groundbreaking solution that integrates machine learning and remote sensing data, challenging traditional closed chamber methods. To achieve this, our methodology involves extensive data collection using drones equipped with a Micasense Altum camera and ground sensors, effectively reducing reliance on labor-intensive and costly field sampling. In this experimental project, our research delves into the intricate relationship between environmental variables, such as soil conditions and weather patterns, and CH4 emissions. We achieved remarkable results by utilizing unmanned aerial vehicles (UAV) and evaluating over 20 regression models, emphasizing an R2 value of 0.98 and 0.95 for the training and testing data, respectively. This outcome designates the random forest regressor as the most suitable model with superior predictive capabilities. Notably, phosphorus, GRVI median, and cumulative soil and water temperature emerged as the model's fittest variables for predicting these values. Our findings underscore an innovative, cost-effective, and efficient alternative for quantifying CH4 emissions, marking a significant advancement in the technology-driven approach to evaluating rice growth parameters and vegetation indices, providing valuable insights for advancing gas emissions studies in rice paddies.

Comparative Analysis of Detectors and Feature Descriptors for Multispectral Image Matching in Rice Crops.

Precision agriculture has greatly benefited from advances in machine vision and image processing techniques. The use of feature descriptors and detectors allows to find distinctive keypoints in an image and the use of this approach for agronomical applications has become a widespread field of study. By combining near infrared (NIR) images, acquired with a modified Nikon D80 camera, and visible spectrum (VIS) images, acquired with a Nikon D300s, a proper crop identification could be obtained. Still, the use of different sensors brings an image matching challenge due to the difference between cameras and the possible distortions from each imaging technique. The aim of this paper is to compare the performance of several feature descriptors and detectors by comparing near infrared and visual spectral bands in rice crop images. Therefore, a group of 20 different scenes with different cameras and growth stages in a rice crop were evaluated. Thus, red, green, blue (RGB) and L, a, b (CIE L*a*b*) channels were extracted from VIS images in order to compare the matches obtained between each of them and the corresponding NIR image. The BRISK, SURF, SIFT, ORB, KAZE, and AKAZE methods were implemented, which act as descriptors and detectors. Additionally, a combination was made between the FAST algorithm for the detection of keypoints with the BRIEF, BRISK, and FREAK methods for features description. BF and FLANN matching methods were used. The algorithms were implemented in Python using OpenCV library. The green channel presented the highest number of correct matches in all methods. In turn, the method that presented the highest performance both in time and in the number of correct matches was the combination of the FAST feature detector and the BRISK descriptor.

Field-transcriptome analyses reveal developmental transitions during flowering in cassava (Manihot esculenta Crantz).

KEY MESSAGE: We characterized genes that function in the photoperiodic flowering pathway in cassava. Transcriptome analysis of field-grown plants revealed characteristic expression patterns of these genes, demonstrating that field-grown cassava experiences two distinct developmental transitions. Cassava is an important crop for both edible and industrial purposes. Cassava develops storage roots that accumulate starch, providing an important source of staple food in tropical regions. To facilitate cassava breeding, it is important to elucidate how flowering is controlled. Several important genes that control flowering time have been identified in model plants; however, comprehensive characterization of these genes in cassava is still lacking. In this study, we identified genes encoding central flowering time regulators and examined these sequences for the presence or absence of conserved motifs. We found that cassava shares conserved genes for the photoperiodic flowering pathway, including florigen, anti-florigen and its associated transcription factor (GIGANTEA, CONSTANS, FLOWERING LOCUS T, CENTRORADIALIS/TERMINAL FLOWER1 and FD) and florigen downstream genes (SUPRESSOR OF OVEREXPRESSION OF CONSTANS1 and APETALA1/FRUITFUL). We conducted RNA-seq analysis of field-grown cassava plants and characterized the expression of flowering control genes. Finally, from the transcriptome analysis we identified two distinct developmental transitions that occur in field-grown cassava.

Machine learning for high-throughput field phenotyping and image processing provides insight into the association of above and below-ground traits in cassava (Manihot esculenta Crantz).

BACKGROUND: Rapid non-destructive measurements to predict cassava root yield over the full growing season through large numbers of germplasm and multiple environments is a huge challenge in Cassava breeding programs. As opposed to waiting until the harvest season, multispectral imagery using unmanned aerial vehicles (UAV) are capable of measuring the canopy metrics and vegetation indices (VIs) traits at different time points of the growth cycle. This resourceful time series aerial image processing with appropriate analytical framework is very important for the automatic extraction of phenotypic features from the image data. Many studies have demonstrated the usefulness of advanced remote sensing technologies coupled with machine learning (ML) approaches for accurate prediction of valuable crop traits. Until now, Cassava has received little to no attention in aerial image-based phenotyping and ML model testing. RESULTS: To accelerate image processing, an automated image-analysis framework called CIAT Pheno-i was developed to extract plot level vegetation indices/canopy metrics. Multiple linear regression models were constructed at different key growth stages of cassava, using ground-truth data and vegetation indices obtained from a multispectral sensor. Henceforth, the spectral indices/features were combined to develop models and predict cassava root yield using different Machine learning techniques. Our results showed that (1) Developed CIAT pheno-i image analysis framework was found to be easier and more rapid than manual methods. (2) The correlation analysis of four phenological stages of cassava revealed that elongation (EL) and late bulking (LBK) were the most useful stages to estimate above-ground biomass (AGB), below-ground biomass (BGB) and canopy height (CH). (3) The multi-temporal analysis revealed that cumulative image feature information of EL + early bulky (EBK) stages showed a higher significant correlation (r = 0.77) for Green Normalized Difference Vegetation indices (GNDVI) with BGB than individual time points. Canopy height measured on the ground correlated well with UAV (CHuav)-based measurements (r = 0.92) at late bulking (LBK) stage. Among different image features, normalized difference red edge index (NDRE) data were found to be consistently highly correlated (r = 0.65 to 0.84) with AGB at LBK stage. (4) Among the four ML algorithms used in this study, k-Nearest Neighbours (kNN), Random Forest (RF) and Support Vector Machine (SVM) showed the best performance for root yield prediction with the highest accuracy of R2 = 0.67, 0.66 and 0.64, respectively. CONCLUSION: UAV platforms, time series image acquisition, automated image analytical framework (CIAT Pheno-i), and key vegetation indices (VIs) to estimate phenotyping traits and root yield described in this work have great potential for use as a selection tool in the modern cassava breeding programs around the world to accelerate germplasm and varietal selection. The image analysis software (CIAT Pheno-i) developed from this study can be widely applicable to any other crop to extract phenotypic information rapidly.

Expression of the CCCH-tandem zinc finger protein gene OsTZF5 under a stress-inducible promoter mitigates the effect of drought stress on rice grain yield under field conditions.

Increasing drought resistance without sacrificing grain yield remains an ongoing challenge in crop improvement. In this study, we report that Oryza sativa CCCH-tandem zinc finger protein 5 (OsTZF5) can confer drought resistance and increase grain yield in transgenic rice plants. Expression of OsTZF5 was induced by abscisic acid, dehydration and cold stress. Upon stress, OsTZF5-GFP localized to the cytoplasm and cytoplasmic foci. Transgenic rice plants overexpressing OsTZF5 under the constitutive maize ubiquitin promoter exhibited improved survival under drought but also growth retardation. By introducing OsTZF5 behind the stress-responsive OsNAC6 promoter in two commercial upland cultivars, Curinga and NERICA4, we obtained transgenic plants that showed no growth retardation. Moreover, these plants exhibited significantly increased grain yield compared to non-transgenic cultivars in different confined field drought environments. Physiological analysis indicated that OsTZF5 promoted both drought tolerance and drought avoidance. Collectively, our results provide strong evidence that OsTZF5 is a useful biotechnological tool to minimize yield losses in rice grown under drought conditions.

A low-cost aeroponic phenotyping system for storage root development: unravelling the below-ground secrets of cassava (Manihot esculenta).

BACKGROUND: Root and tuber crops are becoming more important for their high source of carbohydrates, next to cereals. Despite their commercial impact, there are significant knowledge gaps about the environmental and inherent regulation of storage root (SR) differentiation, due in part to the innate problems of studying storage roots and the lack of a suitable model system for monitoring storage root growth. The research presented here aimed to develop a reliable, low-cost effective system that enables the study of the factors influencing cassava storage root initiation and development. RESULTS: We explored simple, low-cost systems for the study of storage root biology. An aeroponics system described here is ideal for real-time monitoring of storage root development (SRD), and this was further validated using hormone studies. Our aeroponics-based auxin studies revealed that storage root initiation and development are adaptive responses, which are significantly enhanced by the exogenous auxin supply. Field and histological experiments were also conducted to confirm the auxin effect found in the aeroponics system. We also developed a simple digital imaging platform to quantify storage root growth and development traits. Correlation analysis confirmed that image-based estimation can be a surrogate for manual root phenotyping for several key traits. CONCLUSIONS: The aeroponic system developed from this study is an effective tool for examining the root architecture of cassava during early SRD. The aeroponic system also provided novel insights into storage root formation by activating the auxin-dependent proliferation of secondary xylem parenchyma cells to induce the initial root thickening and bulking. The developed system can be of direct benefit to molecular biologists, breeders, and physiologists, allowing them to screen germplasm for root traits that correlate with improved economic traits.

Translocation of a parthenogenesis gene candidate to an alternate carrier chromosome in apomictic Brachiaria humidicola.

BACKGROUND: The apomictic reproductive mode of Brachiaria (syn. Urochloa) forage species allows breeders to faithfully propagate heterozygous genotypes through seed over multiple generations. In Brachiaria, reproductive mode segregates as single dominant locus, the apospory-specific genomic region (ASGR). The AGSR has been mapped to an area of reduced recombination on Brachiaria decumbens chromosome 5. A primer pair designed within ASGR-BABY BOOM-like (BBML), the candidate gene for the parthenogenesis component of apomixis in Pennisetum squamulatum, was diagnostic for reproductive mode in the closely related species B. ruziziensis, B. brizantha, and B. decumbens. In this study, we used a mapping population of the distantly related commercial species B. humidicola to map the ASGR and test for conservation of ASGR-BBML sequences across Brachiaria species. RESULTS: Dense genetic maps were constructed for the maternal and paternal genomes of a hexaploid (2n = 6x = 36) B. humidicola F1 mapping population (n = 102) using genotyping-by-sequencing, simple sequence repeat, amplified fragment length polymorphism, and transcriptome derived single nucleotide polymorphism markers. Comparative genomics with Setaria italica provided confirmation for x = 6 as the base chromosome number of B. humidicola. High resolution molecular karyotyping indicated that the six homologous chromosomes of the sexual female parent paired at random, whereas preferential pairing of subgenomes was observed in the apomictic male parent. Furthermore, evidence for compensated aneuploidy was found in the apomictic parent, with only five homologous linkage groups identified for chromosome 5 and seven homologous linkage groups of chromosome 6. The ASGR mapped to B. humidicola chromosome 1, a region syntenic with chromosomes 1 and 7 of S. italica. The ASGR-BBML specific PCR product cosegregated with the ASGR in the F1 mapping population, despite its location on a different carrier chromosome than B. decumbens. CONCLUSIONS: The first dense molecular maps of B. humidicola provide strong support for cytogenetic evidence indicating a base chromosome number of six in this species. Furthermore, these results show conservation of the ASGR across the Paniceae in different chromosomal backgrounds and support postulation of the ASGR-BBML as candidate genes for the parthenogenesis component of apomixis.

Expression of the Aeluropus littoralis AlSAP Gene Enhances Rice Yield under Field Drought at the Reproductive Stage.

We evaluated the yields of Oryza sativa L. 'Nipponbare' rice lines expressing a gene encoding an A20/AN1 domain stress-associated protein, AlSAP, from the halophyte grass Aeluropus littoralis under the control of different promoters. Three independent field trials were conducted, with drought imposed at the reproductive stage. In all trials, the two transgenic lines, RN5 and RN6, consistently out-performed non-transgenic (NT) and wild-type (WT) controls, providing 50-90% increases in grain yield (GY). Enhancement of tillering and panicle fertility contributed to this improved GY under drought. In contrast with physiological records collected during previous greenhouse dry-down experiments, where drought was imposed at the early tillering stage, we did not observe significant differences in photosynthetic parameters, leaf water potential, or accumulation of antioxidants in flag leaves of AlSAP-lines subjected to drought at flowering. However, AlSAP expression alleviated leaf rolling and leaf drying induced by drought, resulting in increased accumulation of green biomass. Therefore, the observed enhanced performance of the AlSAP-lines subjected to drought at the reproductive stage can be tentatively ascribed to a primed status of the transgenic plants, resulting from a higher accumulation of biomass during vegetative growth, allowing reserve remobilization and maintenance of productive tillering and grain filling. Under irrigated conditions, the overall performance of AlSAP-lines was comparable with, or even significantly better than, the NT and WT controls. Thus, AlSAP expression inflicted no penalty on rice yields under optimal growth conditions. Our results support the use of AlSAP transgenics to reduce rice GY losses under drought conditions.

Overexpression of an Arabidopsis thaliana galactinol synthase gene improves drought tolerance in transgenic rice and increased grain yield in the field.

Drought stress has often caused significant decreases in crop production which could be associated with global warming. Enhancing drought tolerance without a grain yield penalty has been a great challenge in crop improvement. Here, we report the Arabidopsis thaliana galactinol synthase 2 gene (AtGolS2) was able to confer drought tolerance and increase grain yield in two different rice (Oryza sativa) genotypes under dry field conditions. The developed transgenic lines expressing AtGolS2 under the control of the constitutive maize ubiquitin promoter (Ubi:AtGolS2) also had higher levels of galactinol than the non-transgenic control. The increased grain yield of the transgenic rice under drought conditions was related to a higher number of panicles, grain fertility and biomass. Extensive confined field trials using Ubi:AtGolS2 transgenic lines in Curinga, tropical japonica and NERICA4, interspecific hybrid across two different seasons and environments revealed the verified lines have the proven field drought tolerance of the Ubi:AtGolS2 transgenic rice. The amended drought tolerance was associated with higher relative water content of leaves, higher photosynthesis activity, lesser reduction in plant growth and faster recovering ability. Collectively, our results provide strong evidence that AtGolS2 is a useful biotechnological tool to reduce grain yield losses in rice beyond genetic differences under field drought stress.

Development and field performance of nitrogen use efficient rice lines for Africa.

Nitrogen (N) fertilizers are a major input cost in rice production, and its excess application leads to major environmental pollution. Development of rice varieties with improved nitrogen use efficiency (NUE) is essential for sustainable agriculture. Here, we report the results of field evaluations of marker-free transgenic NERICA4 (New Rice for Africa 4) rice lines overexpressing barley alanine amino transferase (HvAlaAT) under the control of a rice stress-inducible promoter (pOsAnt1). Field evaluations over three growing seasons and two rice growing ecologies (lowland and upland) revealed that grain yield of pOsAnt1:HvAlaAT transgenic events was significantly higher than sibling nulls and wild-type controls under different N application rates. Our field results clearly demonstrated that this genetic modification can significantly increase the dry biomass and grain yield compared to controls under limited N supply. Increased yield in transgenic events was correlated with increased tiller and panicle number in the field, and evidence of early establishment of a vigorous root system in hydroponic growth. Our results suggest that expression of the HvAlaAT gene can improve NUE in rice without causing undesirable growth phenotypes. The NUE technology described in this article has the potential to significantly reduce the need for N fertilizer and simultaneously improve food security, augment farm economics and mitigate greenhouse gas emissions from the rice ecosystem.

Identification of QTLs for pod and kernel traits in cultivated peanut by bulked segregant analysis

Bulked segregant analysis was used to identify simple sequence repeat (SSR) markers associated with pod and kernel traits in cultivated peanut, to permit rapid selection of superior quality genotypes in the breeding program. SSR markers linked to pod and kernel traits were identified in two DNA pools (high and low), which were established using selected F2:6 recombinant individuals resulting from a cultivated cross between a runner (Tamrun OL01) and a Spanish (BSS 56) peanut. To identify quantitative trait loci (QTLs) for pod and kernel-related traits, parents were screened initially with 112 SSR primer pairs. The survey revealed 8.9 percent polymorphism between parents. Of ten SSR primer pairs distinguishing the parents, five (PM375, PM36, PM45, pPGPseq8D9, and Ah-041) were associated with differences between bulks for seed length, pod length, number of pods per plant, 100-seed weight, maturity, or oil content. Association was confirmed by analysis of segregation among 88 F2:6 individuals in the RIL population. Phenotypic means associated with markers for three traits differed by more than 40 percent, indicating the presence of QTLs with major effects for number of pods per plant, plant weight, and pod maturity. The SSR markers can be used for marker assisted selection for quality and yield improvement in peanut. To the best of our knowledge, this is the first report on the identification of SSR markers linked to pod - and kernel- related traits in cultivated peanut.

Cloning and characterization of resistance gene analogs from under-exploited plant species

Genomic DNA sequences sharing homology with NBS region of resistance gene analogs were isolated and characterized from Pongamia glabra, Adenanthera pavonina, Clitoria ternatea and Solanum trilobatum using PCR based approach with primers designed from conserved regions of NBS domain. The presence of consensus motifs viz., kinase 1a, kinase 2, kinase 3a and hydrophobic domain provided evidence that the cloned sequences may belong to the NBS-LRR gene family. Conservation of tryptophan as the last residue of kinase-2 motif further confirms their position in non-TIR NBS-LRR family of resistance genes. The Resistance Gene Analogs (RGAs) cloned from P. glabra, A. pavonina, C. ternatea and S. trilobatum clustered together with well- characterized non-TIR-NBS-LRR genes leaving the TIR-NBS-LRR genes as a separate cluster in the average distance tree constructed based on BLOSUM62. All the four RGAs had high level of identity with NBS-LRR family of RGAs deposited in the GenBank. The extent of identity between the sequences at NBS region varied from 29 percent (P. glabra and S. trilobatum) to 78 percent (A. pavonina and C. ternatea), which indicates the diversity among the RGAs.