Forests suffer from heavy losses due to the occurrence of fires. A prediction model based on environmental condition, such as meteorological and vegetation indexes, is considered a promising tool to control forest fires. The construction of prediction models can be challenging due to (i) the requirement of selection of features most relevant to the prediction task, and (ii) heavily imbalanced data distribution where the number of large-scale forest fires is much less than that of small-scale ones. In this paper, we propose a forest fire prediction method that employs a sparse autoencoder-based deep neural network and a novel data balancing procedure. The method was tested on a forest fire dataset collected from the Montesinho Natural Park of Portugal. Compared to the best prediction results of other state-of-the-art methods, the proposed method could predict large-scale forest fires more accurately, and reduces the mean absolute error by 3–19.3 and root mean squared error by 0.95–19.3. The proposed method can better benefit the management of wildland fires in advance and the prevention of serious fire accidents. It is expected that the prediction performance could be further improved if additional information and more data are available.

Sequence-related amplified polymorphism (SRAP) markers were used to investigate the genetic diversity among 30 populations of Toona ciliata Roem. sampled from the species’ distribution area in China. To analyze the polymorphism in the SRAP profiles, 1505 primer pairs were screened and 24 selected. A total of 656 SRAP bands ranging from 100 to 1500 bp were acquired, of these 505 bands (77%) were polymorphic. The polymorphism information content (PIC) values ranged from 0.32 to 0.45, with an average of 0.41. An analysis of molecular variance (AMOVA) indicated that the most significant variation was attributable to differences among the populations and that variation within the populations was small. STRUCTURE analysis divided the 30 populations into two parts. The unweighted pair group method of arithmetic averages (UPGMA) clustering and principal coordinates analysis (PCoA) showed that the 30 populations could be classified into four types. The results demonstrate a clear geographical trend for T. ciliata in China and provide a theoretical basis for future breeding and conservation strategy of T. ciliata.

Aluminum (Al) affects the yield of forest trees in acidic soils. The oil tea plant (Camellia drupifera Lour.) has high Al tolerance, with abundant phenolic compounds in its leaves, especially flavonoid compounds. The role of these flavonoids in the Al resistance of oil tea plants is unclear. In this metabolomic study of C. drupifera under Al stress, ultra-pressure liquid chromatography coupled with tandem mass spectrometry (UPLC-MS/MS) was utilized to identify metabolites, while principal component analysis, cluster analysis, and orthogonal partial least squares discriminant analysis were applied to analyze the data on the flavonoid metabolites. The leaf morphology of C. drupifera revealed significant damage by excess aluminum ions under each treatment compared with the control group. Under Al stress at 2 mmol/L (GZ2) and 4 mmol/L (GZ4), the total flavonoid content in C. drupifera leaves reached 24.37 and 35.64 mg/g, respectively, which are significantly higher than the levels measured in the control group (CK) (p < 0.01). In addition, we identified 25 upregulated and 5 downregulated metabolites in the GZ2 vs. CK comparison and 31 upregulated and 7 downregulated flavonoid metabolites in GZ4 vs. CK. The results demonstrate that different levels of Al stress had a significant influence on the metabolite profile of C. drupifera. It was found that the abundance of the 24 differential flavonoid metabolites was gradually elevated with increasing concentrations of Al stress, including catechin, epicatechin, naringenin-7-glucoside, astilbin, taxifolin, miquelianin, quercitrin, and quercimeritrin. Moreover, the most significant increase in antioxidant activity (about 30%) was observed in C. drupifera precultured in leaf extracts containing 7.5 and 15 μg/mL of active flavonoids. The qRT-PCR results showed that the expression levels of key genes involved in the synthesis of flavonoids were consistent with the accumulation trends of flavonoids under different concentrations of Al. Therefore, our results demonstrate the key role of flavonoid compounds in the oil tea plant C. drupifera in response to Al stress, which suggests that flavonoid metabolites in C. drupifera, as well as other aluminum-tolerant plants, may help with detoxifying aluminum.

The uncertainty about whether, in China, the genus Melia (Meliaceae) consists of one species (M. azedarach Linnaeus) or two species (M. azedarach and M. toosendan Siebold & Zuccarini) remains to be clarified. Although the two putative species are morphologically distinguishable, genetic evidence supporting their taxonomic separation is lacking. Here, we investigated the genetic diversity and population structure of 31 Melia populations across the natural distribution range of the genus in China. We used sequence-related amplified polymorphism (SRAP) markers and obtained 257 clearly defined bands amplified by 20 primers from 461 individuals. The polymorphic loci (P) varied from 35.17% to 76.55%, with an overall mean of 58.24%. Nei’s gene diversity (H) ranged from 0.13 to 0.31, with an overall mean of 0.20. Shannon’s information index (I) ranged from 0.18 to 0.45, with an average of 0.30. The genetic diversity of the total population (H_t) and within populations (H_s) was 0.37 ± 0.01 and 0.20 ± 0.01, respectively. Population differentiation was substantial (Gst = 0.45), and gene flow was low. Of the total variation, 31.41% was explained by differences among putative species, 19.17% among populations within putative species, and 49.42% within populations. Our results support the division of genus Melia into two species, which is consistent with the classification based on the morphological differentiation.

Morinda officinalis How (Rubiaceae) is well known as one of the four most popular medicinal plants in the southern region of China. In order to assess its genetic diversity and assist the development of its molecular assisted-selection breeding in China, we constructed the transcriptome database of M. officinalis using fresh leaf material and developed novel expressed sequence tag–simple sequence repeat (EST-SSR) markers for this important medicinal plant species. Our study identified 8064 potential EST-SSRs from 6668 unigenes. For perfect repeat motifs, the mononucleotide repeats were most abundant (4221; 52.34%), followed by the trinucleotide repeats (1588; 19.69%), and the dinucleotide ones (1040; 12.90%). The seven most commonly occurring repeat motifs were A/T (4661), AG/CT (588), AAG/CTT (408), AC/GT (353), ATC/ATG (338), AT/AT (296) and AGG/CCT (277). Of a total of 5605 SSR primer sets that were successfully designed de novo, 100 were selected for validation analysis. There, 24 primer sets were polymorphic across the 96 M. officinalis individuals collected from four different populations in Guangdong province. Based on cross-species transferability test, 19 and 22 primer sets produced successful amplification in M. umbellata subsp. obovata and M. parvifolia, respectively. These novel EST-SSR markers with high cross-species transferability between M. officinalis and its closely-related species could serve as aids to future studies in genetic diversity, conservation, assisted-selection breeding and genes associated with the medical uses of the genus.

The seeds of Camellia oleifera produce high amount of oil, which can be broadly used in the fields of food, industry, and medicine. However, the molecular regulation mechanisms of seed development and oil accumulation in C. oleifera are unclear. In this study, evolutionary and expression analyses of the MADS‐box gene family were performed across the C. oleifera genome for the first time. A total of 86 MADS‐box genes (ColMADS) were identified, including 60 M‐type and 26 MIKC members. More gene duplication events occurred in M‐type subfamily (6) than that in MIKC subfamily (2), and SEP-like genes were lost from the MIKC^C clade. Furthermore, 8, 15, and 17 differentially expressed ColMADS genes (DEGs) were detected between three developmental stages of seed (S1/S2, S2/S3, and S1/S3), respectively. Among these DEGs, the STK-like ColMADS12 and TT16-like ColMADS17 were highly expressed during the seed formation (S1 and S2), agreeing with their predicted functions to positively regulate the seed organogenesis and oil accumulation. While ColMADS57 and ColMADS07 showed increasing expression level with the seed maturation (S2 and S3), conforming to their potential roles in promoting the seed ripening. In all, these results revealed a critical role of MADS‐box genes in the C. oleifera seed development and oil accumulation, which will contribute to the future molecular breeding of C. oleifera.